Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi...Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.展开更多
Root architecture,which determines the water and nutrient uptake ability of crops,is highly plastic in response to soil environmental changes and different cultivation patterns.Root phenotyping for field-grown crops,e...Root architecture,which determines the water and nutrient uptake ability of crops,is highly plastic in response to soil environmental changes and different cultivation patterns.Root phenotyping for field-grown crops,especially topological trait extraction,is rarely performed.In this study,an image-based semi-automatic root phenotyping method for field-grown crops was developed.The method consisted of image acquisition,image denoising and segmentation,trait extraction and data analysis.Five global traits and 40 local traits were extracted with this method.A good consistency in 1st-order lateral root branching was observed between the visually counted values and the values extracted using the developed method,with R^(2)=0.97.Using the method,we found that the interspecific advantages for maize mainly occurred within 5 cm from the root base in the nodal roots of the 5th-7th nodes,and that the obvious inhibition of soybean was mostly reflected within 20 cm from the root base.Our study provides a novel approach with high-throughput and high-accuracy for field research on root morphology and branching features.It could be applied to the 3D reconstruction of field-grown root system architecture to improve the inputs to data-driven models(e.g.,OpenSimRoot)that simulate root growth,solute transport and water uptake.展开更多
Since real world communication channels are not error free, the coded data transmitted on them may be corrupted, and block based image coding systems are vulnerable to transmission impairment. So the best neighborh...Since real world communication channels are not error free, the coded data transmitted on them may be corrupted, and block based image coding systems are vulnerable to transmission impairment. So the best neighborhood match method using genetic algorithm is used to conceal the error blocks. Experimental results show that the searching space can be greatly reduced by using genetic algorithm compared with exhaustive searching method, and good image quality is achieved. The peak signal noise ratios(PSNRs) of the restored images are increased greatly.展开更多
Spike number(SN) per unit area is one of the major determinants of grain yield in wheat. Development of high-throughput techniques to count SN from large populations enables rapid and cost-effective selection and faci...Spike number(SN) per unit area is one of the major determinants of grain yield in wheat. Development of high-throughput techniques to count SN from large populations enables rapid and cost-effective selection and facilitates genetic studies. In the present study, we used a deep-learning algorithm, i.e., Faster Region-based Convolutional Neural Networks(Faster R-CNN) on Red-Green-Blue(RGB) images to explore the possibility of image-based detection of SN and its application to identify the loci underlying SN. A doubled haploid population of 101 lines derived from the Yangmai 16/Zhongmai 895 cross was grown at two sites for SN phenotyping and genotyped using the high-density wheat 660 K SNP array.Analysis of manual spike number(MSN) in the field, image-based spike number(ISN), and verification of spike number(VSN) by Faster R-CNN revealed significant variation(P < 0.001) among genotypes, with high heritability ranged from 0.71 to 0.96. The coefficients of determination(R^(2)) between ISN and VSN was 0.83, which was higher than that between ISN and MSN(R^(2)= 0.51), and between VSN and MSN(R^(2)= 0.50). Results showed that VSN data can effectively predict wheat spikes with an average accuracy of 86.7% when validated using MSN data. Three QTL Qsnyz.caas-4 DS, Qsnyz.caas-7 DS, and QSnyz.caas-7 DL were identified based on MSN, ISN and VSN data, while QSnyz.caas-7 DS was detected in all the three data sets. These results indicate that using Faster R-CNN model for image-based identification of SN per unit area is a precise and rapid phenotyping method, which can be used for genetic studies of SN in wheat.展开更多
Inclusion of textures in image classification has been shown beneficial.This paper studies an efficient use of semivariogram features for object-based high-resolution image classification.First,an input image is divid...Inclusion of textures in image classification has been shown beneficial.This paper studies an efficient use of semivariogram features for object-based high-resolution image classification.First,an input image is divided into segments,for each of which a semivariogram is then calculated.Second,candidate features are extracted as a number of key locations of the semivariogram functions.Then we use an improved Relief algorithm and the principal component analysis to select independent and significant features.Then the selected prominent semivariogram features and the conventional spectral features are combined to constitute a feature vector for a support vector machine classifier.The effect of such selected semivariogram features is compared with those of the gray-level co-occurrence matrix(GLCM)features and window-based semivariogram texture features(STFs).Tests with aerial and satellite images show that such selected semivariogram features are of a more beneficial supplement to spectral features.The described method in this paper yields a higher classification accuracy than the combination of spectral and GLCM features or STFs.展开更多
The diagnostic potential of brain positron emission tomography （PET） imaging is limited by low spatial resolution. For solving this problem we propose a technique for the fusion of PET and MRI images. This fusion is...The diagnostic potential of brain positron emission tomography （PET） imaging is limited by low spatial resolution. For solving this problem we propose a technique for the fusion of PET and MRI images. This fusion is a trade-off between the spectral information extracted from PET images and the spatial information extracted from high spatial resolution MRI. The proposed method can control this trade-off. To achieve this goal, it is necessary to build a multiscale fusion model, based on the retinal cell photoreceptors model. This paper introduces general prospects of this model, and its application in multispectral medical image fusion. Results showed that the proposed method preserves more spectral features with less spatial distortion. Comparing with hue-intensity-saturation （HIS）, discrete wavelet transform （DWT）, wavelet-based sharpening and wavelet-a trous transform methods, the best spectral and spatial quality is only achieved simultaneously with the proposed feature-based data fusion method. This method does not require resampling images, which is an advantage over the other methods, and can perform in any aspect ratio between the pixels of MRI and PET images.展开更多
A new techinque for color based image retrieval is proposed. In this technique, the whole spectrum of a color image is divided into several sub ranges according to human visual characteristics. Then for each sub ra...A new techinque for color based image retrieval is proposed. In this technique, the whole spectrum of a color image is divided into several sub ranges according to human visual characteristics. Then for each sub range, the cumulative histogram is used for similarity matching. It is shown that the color contents of image can be well captured by the sub range cumulative histogram. The new technique has been tested and compared with conventional techniques with the help of a database of 400 images of real flowers, which are quite complicated in color contents. Some satisfactory retrieval results are presented.展开更多
Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based ...Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based on field image gray projection which enables the regional odd and even field image to be projected into x and y directions and thus to get the regional gray projection curves in x and y directions,respectively.For the odd field image channel,motion parameters can be estimated via iterative minimum absolute difference based on two successive field image regional gray projection curves.Then motion compensations can be obtained after using the Kalman filter method.Finally,the odd field image is adjusted according to the compensations.In the mean time,motion compensation is applied to the even field image channel with the odd field image gray projection curves of the current frame.By minimizing absolute difference between odd and even field image gray projection curves of the current frame,the inter-field motion parameters can be estimated.Therefore,the even field image can be adjusted by combining the inter-field motion parameters and the odd field compensations.Finally,the stabilized image sequence can be obtained by synthesizing the adjusted odd and even field images.Experimental results show that the proposed algorithm can run in real-time and have a good stabilization performance.In addition,image blurring can be improved.展开更多
In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters ...In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters out many noisy features in the first stage. Then the new ranking criterion based on SVM-RFE method is applied to obtain the final feature subset. The SVM classifier is used to evaluate the final image classification accuracy. Experimental results show that our proposed relief- SVM-RFE algorithm can achieve significant improvements for feature selection in image classification.展开更多
Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate...Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate promising results but always need ground object filtered DEM generation before otho-rectification;this can consume much time and produce building facade contained results.To address this problem,a pixel-by-pixel digital differential rectification-based automatic DOM generation method is proposed in this paper.Firstly,3D point clouds with texture are generated by dense image matching based on an optical flow field for a stereo pair of images,respectively.Then,the grayscale of the digital differential rectification image is extracted directly from the point clouds element by element according to the nearest neighbor method for matched points.Subsequently,the elevation is repaired grid-by-grid using the multi-layer Locally Refined B-spline(LR-B)interpolation method with triangular mesh constraint for the point clouds void area,and the grayscale is obtained by the indirect scheme of digital differential rectification to generate the pixel-by-pixel digital differentially rectified image of a single image slice.Finally,a seamline network is automatically searched using a disparity map optimization algorithm,and DOM is smartly mosaicked.The qualitative and quantitative experimental results on three datasets were produced and evaluated,which confirmed the feasibility of the proposed method,and the DOM accuracy can reach 1 Ground Sample Distance(GSD)level.The comparison experiment with the state-of-the-art commercial softwares showed that the proposed method generated DOM has a better visual effect on building boundaries and roof completeness with comparable accuracy and computational efficiency.展开更多
A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV col...A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV color space to get the V channel. Next, the illuminations are respectively estimated by the guided filtering and the variational framework on the V channel and combined into a new illumination by average gradient. The new reflectance is calculated using V channel and the new illumination. Then a new V channel obtained by multiplying the new illumination and reflectance is processed with contrast limited adaptive histogram equalization(CLAHE). Finally, the new image in HSV space is converted back to RGB space to obtain the enhanced image. Experimental results show that the proposed method has better subjective quality and objective quality than existing methods.展开更多
Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wi...Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.展开更多
In this work, image feature vectors are formed for blocks containing sufficient information, which are selected using a singular-value criterion. When the ratio between the first two SVs axe below a given threshold, t...In this work, image feature vectors are formed for blocks containing sufficient information, which are selected using a singular-value criterion. When the ratio between the first two SVs axe below a given threshold, the block is considered informative. A total of 12 features including statistics of brightness, color components and texture measures are used to form intermediate vectors. Principal component analysis is then performed to reduce the dimension to 6 to give the final feature vectors. Relevance of the constructed feature vectors is demonstrated by experiments in which k-means clustering is used to group the vectors hence the blocks. Blocks falling into the same group show similar visual appearances.展开更多
The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is propos...The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.展开更多
The use of massive image databases has increased drastically over the few years due to evolution of multimedia technology.Image retrieval has become one of the vital tools in image processing applications.Content-Base...The use of massive image databases has increased drastically over the few years due to evolution of multimedia technology.Image retrieval has become one of the vital tools in image processing applications.Content-Based Image Retrieval(CBIR)has been widely used in varied applications.But,the results produced by the usage of a single image feature are not satisfactory.So,multiple image features are used very often for attaining better results.But,fast and effective searching for relevant images from a database becomes a challenging task.In the previous existing system,the CBIR has used the combined feature extraction technique using color auto-correlogram,Rotation-Invariant Uniform Local Binary Patterns(RULBP)and local energy.However,the existing system does not provide significant results in terms of recall and precision.Also,the computational complexity is higher for the existing CBIR systems.In order to handle the above mentioned issues,the Gray Level Co-occurrence Matrix(GLCM)with Deep Learning based Enhanced Convolution Neural Network(DLECNN)is proposed in this work.The proposed system framework includes noise reduction using histogram equalization,feature extraction using GLCM,similarity matching computation using Hierarchal and Fuzzy c-Means(HFCM)algorithm and the image retrieval using DLECNN algorithm.The histogram equalization has been used for computing the image enhancement.This enhanced image has a uniform histogram.Then,the GLCM method has been used to extract the features such as shape,texture,colour,annotations and keywords.The HFCM similarity measure is used for computing the query image vector's similarity index with every database images.For enhancing the performance of this image retrieval approach,the DLECNN algorithm is proposed to retrieve more accurate features of the image.The proposed GLCM+DLECNN algorithm provides better results associated with high accuracy,precision,recall,f-measure and lesser complexity.From the experimental results,it is clearly observed that the proposed system provides efficient image retrieval for the given query image.展开更多
A method of color image single-channel encryption is proposed. The proposed method uses tricolor grating to encode a color image into a gray level image, then the gray level image is encrypted by double random phase e...A method of color image single-channel encryption is proposed. The proposed method uses tricolor grating to encode a color image into a gray level image, then the gray level image is encrypted by double random phase encryption, so a color image is encrypted in a single-channel and its security is ensured. Computer simulations and the chromatic aberration analysis are given to prove the possibility of the proposed idea.The optical system is simpler and is easy to be applied into practice. The simulation resu...展开更多
t LBS （location-based service） is a remarkable outcome of the development from GIS to geospatial information service. Faced by the requirements of geospatial information from the masses and the opportunity provided ...t LBS （location-based service） is a remarkable outcome of the development from GIS to geospatial information service. Faced by the requirements of geospatial information from the masses and the opportunity provided by the next generation lnternet and Web 2.0, a new model of geospatial information service based on DMI （digital measurable image） is presented. First, the con- cept of LBS and the opportunities of Web 2.0 are introduced, then the characteristic of DMI is discussed. Taking the Image City.Wuhan as an example, the function ofgeospatial information service based on DM! is introduced. Finally, the feasibility for its industrialization is discussed.展开更多
A hierarchical structure method of content based image retrieval was proposed. During image preprocessing stage three semi automatic algorithms were used to extract image regions. String matching can be used to redu...A hierarchical structure method of content based image retrieval was proposed. During image preprocessing stage three semi automatic algorithms were used to extract image regions. String matching can be used to reduce image searching range. Smallest enclose rectangle(SER) and Hausdorff distance under region normalization were used to measure the similarity between trademark images while keeping invariant under transform(translation, rotation and scale) and noise tolerant. The experiment results show its efficiency.展开更多
Plants respond to drought stress with different physical manners, such as morphology and color of leaves. Thus, plants can be considered as a sort of living-sensors for monitoring dynamic of soil water content or the ...Plants respond to drought stress with different physical manners, such as morphology and color of leaves. Thus, plants can be considered as a sort of living-sensors for monitoring dynamic of soil water content or the stored water in plant body. Because of difficulty to identify the early wilting symptom of plants from the results in 2D （two-dimension） space, this paper presented a preliminary study with 3D （three-dimension）-based image, in which a laser scanner was used for achieving the morphological information of zucchini （Cucurbita pepo） leaves. Moreover, a leaf wilting index （DLWIF） was defined by fractal dimension. The experiment consisted of phase-1 for observing the temporal variation of DLWIF and phase-2 for the validation of this index. During the experiment, air temperature, luminous intensity, and volumetric soil water contents （VSWC） were simultaneously recorded over time. The results of both phases fitted the bisector （line： 1：1） with R2=0.903 and REMS=0.155. More significantly, the influence of VSWC with three levels （0.22, 0.30, and 0.36 cm3 cm-3） on the response of plant samples to drought stress was observed from separated traces of DLWIF. In brief, two conclusions have been made： （i） the laser scanner is an effective tool for the non-contact detection of morphological wilting of plants, and （ii） defined DLWIF can be a promising indicator for a category of plants like zucchini.展开更多
基金funded by University of Transport and Communications(UTC)under grant number T2025-CN-004.
文摘Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.
基金supported by the National Key Research and Development Program of China (2016YFD0300202)the Science and Technology Project of Yunna, China (2017YN07)the Science and Technology Major Project of Inner Mongolia, China (2019ZD024 and 2020GG0038)
文摘Root architecture,which determines the water and nutrient uptake ability of crops,is highly plastic in response to soil environmental changes and different cultivation patterns.Root phenotyping for field-grown crops,especially topological trait extraction,is rarely performed.In this study,an image-based semi-automatic root phenotyping method for field-grown crops was developed.The method consisted of image acquisition,image denoising and segmentation,trait extraction and data analysis.Five global traits and 40 local traits were extracted with this method.A good consistency in 1st-order lateral root branching was observed between the visually counted values and the values extracted using the developed method,with R^(2)=0.97.Using the method,we found that the interspecific advantages for maize mainly occurred within 5 cm from the root base in the nodal roots of the 5th-7th nodes,and that the obvious inhibition of soybean was mostly reflected within 20 cm from the root base.Our study provides a novel approach with high-throughput and high-accuracy for field research on root morphology and branching features.It could be applied to the 3D reconstruction of field-grown root system architecture to improve the inputs to data-driven models(e.g.,OpenSimRoot)that simulate root growth,solute transport and water uptake.
文摘Since real world communication channels are not error free, the coded data transmitted on them may be corrupted, and block based image coding systems are vulnerable to transmission impairment. So the best neighborhood match method using genetic algorithm is used to conceal the error blocks. Experimental results show that the searching space can be greatly reduced by using genetic algorithm compared with exhaustive searching method, and good image quality is achieved. The peak signal noise ratios(PSNRs) of the restored images are increased greatly.
基金funded by the National Natural Science Foundation of China (31671691, 3171101265, and 31961143007)the National Key Research and Development Program of China(2016YFD0101804)the Fundamental Research Funds for the Institute Planning in Chinese Academy of Agricultural Sciences(S2018QY02)。
文摘Spike number(SN) per unit area is one of the major determinants of grain yield in wheat. Development of high-throughput techniques to count SN from large populations enables rapid and cost-effective selection and facilitates genetic studies. In the present study, we used a deep-learning algorithm, i.e., Faster Region-based Convolutional Neural Networks(Faster R-CNN) on Red-Green-Blue(RGB) images to explore the possibility of image-based detection of SN and its application to identify the loci underlying SN. A doubled haploid population of 101 lines derived from the Yangmai 16/Zhongmai 895 cross was grown at two sites for SN phenotyping and genotyped using the high-density wheat 660 K SNP array.Analysis of manual spike number(MSN) in the field, image-based spike number(ISN), and verification of spike number(VSN) by Faster R-CNN revealed significant variation(P < 0.001) among genotypes, with high heritability ranged from 0.71 to 0.96. The coefficients of determination(R^(2)) between ISN and VSN was 0.83, which was higher than that between ISN and MSN(R^(2)= 0.51), and between VSN and MSN(R^(2)= 0.50). Results showed that VSN data can effectively predict wheat spikes with an average accuracy of 86.7% when validated using MSN data. Three QTL Qsnyz.caas-4 DS, Qsnyz.caas-7 DS, and QSnyz.caas-7 DL were identified based on MSN, ISN and VSN data, while QSnyz.caas-7 DS was detected in all the three data sets. These results indicate that using Faster R-CNN model for image-based identification of SN per unit area is a precise and rapid phenotyping method, which can be used for genetic studies of SN in wheat.
基金This work was supported by the National Natural Science Foundation of China[grant number 41101410]the Comprehensive Transportation Applications of High-resolution Remote Sensing program[grant number 07-Y30B10-9001-14/16]+1 种基金the Key Laboratory of Surveying Mapping and Geoinformation in Geographical Condition Monitoring[grant number 2014NGCM]the Science and Technology Plan of Sichuan Bureau of Surveying,Mapping and Geoinformation,China[grant number J2014ZC02].
文摘Inclusion of textures in image classification has been shown beneficial.This paper studies an efficient use of semivariogram features for object-based high-resolution image classification.First,an input image is divided into segments,for each of which a semivariogram is then calculated.Second,candidate features are extracted as a number of key locations of the semivariogram functions.Then we use an improved Relief algorithm and the principal component analysis to select independent and significant features.Then the selected prominent semivariogram features and the conventional spectral features are combined to constitute a feature vector for a support vector machine classifier.The effect of such selected semivariogram features is compared with those of the gray-level co-occurrence matrix(GLCM)features and window-based semivariogram texture features(STFs).Tests with aerial and satellite images show that such selected semivariogram features are of a more beneficial supplement to spectral features.The described method in this paper yields a higher classification accuracy than the combination of spectral and GLCM features or STFs.
基金Project (No. TMU 85-05-33) supported in part by the Iran Telecommunication Research Center (ITRC)
文摘The diagnostic potential of brain positron emission tomography （PET） imaging is limited by low spatial resolution. For solving this problem we propose a technique for the fusion of PET and MRI images. This fusion is a trade-off between the spectral information extracted from PET images and the spatial information extracted from high spatial resolution MRI. The proposed method can control this trade-off. To achieve this goal, it is necessary to build a multiscale fusion model, based on the retinal cell photoreceptors model. This paper introduces general prospects of this model, and its application in multispectral medical image fusion. Results showed that the proposed method preserves more spectral features with less spatial distortion. Comparing with hue-intensity-saturation （HIS）, discrete wavelet transform （DWT）, wavelet-based sharpening and wavelet-a trous transform methods, the best spectral and spatial quality is only achieved simultaneously with the proposed feature-based data fusion method. This method does not require resampling images, which is an advantage over the other methods, and can perform in any aspect ratio between the pixels of MRI and PET images.
文摘A new techinque for color based image retrieval is proposed. In this technique, the whole spectrum of a color image is divided into several sub ranges according to human visual characteristics. Then for each sub range, the cumulative histogram is used for similarity matching. It is shown that the color contents of image can be well captured by the sub range cumulative histogram. The new technique has been tested and compared with conventional techniques with the help of a database of 400 images of real flowers, which are quite complicated in color contents. Some satisfactory retrieval results are presented.
基金supported by the National Natural Science Foundation of China(6110118561302145)
文摘Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based on field image gray projection which enables the regional odd and even field image to be projected into x and y directions and thus to get the regional gray projection curves in x and y directions,respectively.For the odd field image channel,motion parameters can be estimated via iterative minimum absolute difference based on two successive field image regional gray projection curves.Then motion compensations can be obtained after using the Kalman filter method.Finally,the odd field image is adjusted according to the compensations.In the mean time,motion compensation is applied to the even field image channel with the odd field image gray projection curves of the current frame.By minimizing absolute difference between odd and even field image gray projection curves of the current frame,the inter-field motion parameters can be estimated.Therefore,the even field image can be adjusted by combining the inter-field motion parameters and the odd field compensations.Finally,the stabilized image sequence can be obtained by synthesizing the adjusted odd and even field images.Experimental results show that the proposed algorithm can run in real-time and have a good stabilization performance.In addition,image blurring can be improved.
文摘In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters out many noisy features in the first stage. Then the new ranking criterion based on SVM-RFE method is applied to obtain the final feature subset. The SVM classifier is used to evaluate the final image classification accuracy. Experimental results show that our proposed relief- SVM-RFE algorithm can achieve significant improvements for feature selection in image classification.
基金supported by the National Natural Science Foundation of China[Grant No.41771479]the National High-Resolution Earth Observation System(the Civil Part)[Grant No.50-H31D01-0508-13/15]the Japan Society for the Promotion of Science[Grant No.22H03573].
文摘Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate promising results but always need ground object filtered DEM generation before otho-rectification;this can consume much time and produce building facade contained results.To address this problem,a pixel-by-pixel digital differential rectification-based automatic DOM generation method is proposed in this paper.Firstly,3D point clouds with texture are generated by dense image matching based on an optical flow field for a stereo pair of images,respectively.Then,the grayscale of the digital differential rectification image is extracted directly from the point clouds element by element according to the nearest neighbor method for matched points.Subsequently,the elevation is repaired grid-by-grid using the multi-layer Locally Refined B-spline(LR-B)interpolation method with triangular mesh constraint for the point clouds void area,and the grayscale is obtained by the indirect scheme of digital differential rectification to generate the pixel-by-pixel digital differentially rectified image of a single image slice.Finally,a seamline network is automatically searched using a disparity map optimization algorithm,and DOM is smartly mosaicked.The qualitative and quantitative experimental results on three datasets were produced and evaluated,which confirmed the feasibility of the proposed method,and the DOM accuracy can reach 1 Ground Sample Distance(GSD)level.The comparison experiment with the state-of-the-art commercial softwares showed that the proposed method generated DOM has a better visual effect on building boundaries and roof completeness with comparable accuracy and computational efficiency.
基金supported by the China Scholarship CouncilPostgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX17_0776)the Natural Science Foundation of NUPT(No.NY214039)
文摘A new image enhancement algorithm based on Retinex theory is proposed to solve the problem of bad visual effect of an image in low-light conditions. First, an image is converted from the RGB color space to the HSV color space to get the V channel. Next, the illuminations are respectively estimated by the guided filtering and the variational framework on the V channel and combined into a new illumination by average gradient. The new reflectance is calculated using V channel and the new illumination. Then a new V channel obtained by multiplying the new illumination and reflectance is processed with contrast limited adaptive histogram equalization(CLAHE). Finally, the new image in HSV space is converted back to RGB space to obtain the enhanced image. Experimental results show that the proposed method has better subjective quality and objective quality than existing methods.
文摘Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.
基金Project supported by the National Natural Science Foundation of China （Grant No.60502039）, the Shanghai Rising-Star Program （Grant No.06QA14022）, and the Key Project of Shanghai Municipality for Basic Research （Grant No.04JC14037）
文摘In this work, image feature vectors are formed for blocks containing sufficient information, which are selected using a singular-value criterion. When the ratio between the first two SVs axe below a given threshold, the block is considered informative. A total of 12 features including statistics of brightness, color components and texture measures are used to form intermediate vectors. Principal component analysis is then performed to reduce the dimension to 6 to give the final feature vectors. Relevance of the constructed feature vectors is demonstrated by experiments in which k-means clustering is used to group the vectors hence the blocks. Blocks falling into the same group show similar visual appearances.
基金Supported by the National Natural Science Foundation of China (No. 60972106)Postdoctoral Science Foundation (No. 20090450750)the Science Foundation of Tianjin(No. 11JCYBJC00900)
文摘The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.
文摘The use of massive image databases has increased drastically over the few years due to evolution of multimedia technology.Image retrieval has become one of the vital tools in image processing applications.Content-Based Image Retrieval(CBIR)has been widely used in varied applications.But,the results produced by the usage of a single image feature are not satisfactory.So,multiple image features are used very often for attaining better results.But,fast and effective searching for relevant images from a database becomes a challenging task.In the previous existing system,the CBIR has used the combined feature extraction technique using color auto-correlogram,Rotation-Invariant Uniform Local Binary Patterns(RULBP)and local energy.However,the existing system does not provide significant results in terms of recall and precision.Also,the computational complexity is higher for the existing CBIR systems.In order to handle the above mentioned issues,the Gray Level Co-occurrence Matrix(GLCM)with Deep Learning based Enhanced Convolution Neural Network(DLECNN)is proposed in this work.The proposed system framework includes noise reduction using histogram equalization,feature extraction using GLCM,similarity matching computation using Hierarchal and Fuzzy c-Means(HFCM)algorithm and the image retrieval using DLECNN algorithm.The histogram equalization has been used for computing the image enhancement.This enhanced image has a uniform histogram.Then,the GLCM method has been used to extract the features such as shape,texture,colour,annotations and keywords.The HFCM similarity measure is used for computing the query image vector's similarity index with every database images.For enhancing the performance of this image retrieval approach,the DLECNN algorithm is proposed to retrieve more accurate features of the image.The proposed GLCM+DLECNN algorithm provides better results associated with high accuracy,precision,recall,f-measure and lesser complexity.From the experimental results,it is clearly observed that the proposed system provides efficient image retrieval for the given query image.
基金supported by the Opening Subject of KeyLaboratory of Opoelectronic Information Science & Technology,Ministry of Education of China(Grant No. 2005-141)
文摘A method of color image single-channel encryption is proposed. The proposed method uses tricolor grating to encode a color image into a gray level image, then the gray level image is encrypted by double random phase encryption, so a color image is encrypted in a single-channel and its security is ensured. Computer simulations and the chromatic aberration analysis are given to prove the possibility of the proposed idea.The optical system is simpler and is easy to be applied into practice. The simulation resu...
文摘t LBS （location-based service） is a remarkable outcome of the development from GIS to geospatial information service. Faced by the requirements of geospatial information from the masses and the opportunity provided by the next generation lnternet and Web 2.0, a new model of geospatial information service based on DMI （digital measurable image） is presented. First, the con- cept of LBS and the opportunities of Web 2.0 are introduced, then the characteristic of DMI is discussed. Taking the Image City.Wuhan as an example, the function ofgeospatial information service based on DM! is introduced. Finally, the feasibility for its industrialization is discussed.
文摘A hierarchical structure method of content based image retrieval was proposed. During image preprocessing stage three semi automatic algorithms were used to extract image regions. String matching can be used to reduce image searching range. Smallest enclose rectangle(SER) and Hausdorff distance under region normalization were used to measure the similarity between trademark images while keeping invariant under transform(translation, rotation and scale) and noise tolerant. The experiment results show its efficiency.
基金the Chinese-German Center for Scientific Promotion (Chinesisch-Deutsches Zentrum für Wissenschaftsfrderung) under the Project of Sino-German Research Group (GZ494)the Beijing Municipal Education Commission for Building Scientific Research and Scientific Research Base (2008BJKY01)+1 种基金the German Academic Exchange Service (DAAD),and China Scholarship Council (CSC) for enhancing our cooperationthe International Cooperation Fund of Ministry of Science and Technology, China (2010DFA34670)
文摘Plants respond to drought stress with different physical manners, such as morphology and color of leaves. Thus, plants can be considered as a sort of living-sensors for monitoring dynamic of soil water content or the stored water in plant body. Because of difficulty to identify the early wilting symptom of plants from the results in 2D （two-dimension） space, this paper presented a preliminary study with 3D （three-dimension）-based image, in which a laser scanner was used for achieving the morphological information of zucchini （Cucurbita pepo） leaves. Moreover, a leaf wilting index （DLWIF） was defined by fractal dimension. The experiment consisted of phase-1 for observing the temporal variation of DLWIF and phase-2 for the validation of this index. During the experiment, air temperature, luminous intensity, and volumetric soil water contents （VSWC） were simultaneously recorded over time. The results of both phases fitted the bisector （line： 1：1） with R2=0.903 and REMS=0.155. More significantly, the influence of VSWC with three levels （0.22, 0.30, and 0.36 cm3 cm-3） on the response of plant samples to drought stress was observed from separated traces of DLWIF. In brief, two conclusions have been made： （i） the laser scanner is an effective tool for the non-contact detection of morphological wilting of plants, and （ii） defined DLWIF can be a promising indicator for a category of plants like zucchini.
