In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression featu...In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression features is proposed with its objective to describe features in an effective and efficient way in order to improve the recognition performance. The method combines the facial action coding system(FACS) and 'uniform' local binary patterns(LBP) to represent facial expression features from coarse to fine. The facial feature regions are extracted by active shape models(ASM) based on FACS to obtain the gray-level texture. Then, LBP is used to represent expression features for enhancing the discriminant. A facial expression recognition system is developed based on this feature extraction method by using K nearest neighborhood(K-NN) classifier to recognize facial expressions. Finally, experiments are carried out to evaluate this feature extraction method. The significance of removing the unrelated facial regions and enhancing the discrimination ability of expression features in the recognition process is indicated by the results, in addition to its convenience.展开更多
Editors-in-Chief Han-Ping Shi,M.D.,Ph.D.,FACS,Professor of Surgery,Oncology and Nutrition.He is the current Chairman of the Department of GI Surgery/Clinical Nutrition at Beijing Shijitan Hospital,Capital Medical Univ...Editors-in-Chief Han-Ping Shi,M.D.,Ph.D.,FACS,Professor of Surgery,Oncology and Nutrition.He is the current Chairman of the Department of GI Surgery/Clinical Nutrition at Beijing Shijitan Hospital,Capital Medical University,Beijing,China.Dr.Shi received his M.D.degree at the School of Medicine,Wuhan University,Wuhan,and his Ph.D.degree at the Second Military Medical University,Shanghai,China.From 1999 to 2002,Dr.Shi was a postdoc fellow in School of Medicine,Johns Hopkins University,under the supervision of Adrian Barbul,M.D.,FACS,and then in New Jersey Medical School,Rutgers University,under the supervision of Edwin A.Deitch,M.D.,FACS.Dr.Han-ping Shi was the Chairman of the Chinese Society for Parenteral&Enteral Nutrition(CSPEN)between 2018-2021.He is the founder Chairman of the Chinese Society of Nutritional Oncology since 2012,and the director of the Department of Academic,China Anti-Cancer Association(CACA)since 2017.Dr.Han-Ping Shi is currently the founder Editor-in-Chief of Electronic Journal of Metabolism and Nutrition of Cancer(Chinese),founder Editor-in-Chief of Journal of Nutritional Oncology(English)and founder Editor-in-Chief of Precision Nutrition(English).He is also the Associate Editor of Clinical Nutrition,Clinical Nutrition ESPEN,and Journal of Cachexia,Sarcopenia and Muscle,and Nutrition.In 2021 and 2022,he was elected as the top fi ve(second)scholars in the fi eld of nutrition in the whole world by Healsan Consulting,USA.Dr.Han-Ping Shi has published more than 500 academic papers in peer-reviewed Chinese and English journals,and presented more than 1,000 invited talks globally.Dr.Shi was the Editor-in-Chief for 27 books,and he contributed in 53 chapters in 53 books.展开更多
Herein we develop a unique differentiated-uptake strategy capable of efficient and high-purity isolation of genuine drug-resistant(DR)cells from three types of drug-surviving cancer cells,which include paclitaxel-surv...Herein we develop a unique differentiated-uptake strategy capable of efficient and high-purity isolation of genuine drug-resistant(DR)cells from three types of drug-surviving cancer cells,which include paclitaxel-surviving human ovarian OVCAR-3 cancer cells and human lung carcinoma A549/Taxol cells,and doxorubicin-surviving human immortalized myelogenous leukemia K562/ADR cells.By using this strategy which relies on fluorescent glycan nanoparticle(FGNP)-based fluorescence-activated cell sorting(FACS)assays,two subpopulations with distinct fluorescences existing in drug-surviving OVCAR-3 cells were separated,and we found that the lower fluorescence(LF)subpopulation consisted of DR cells,while the higher fluorescence(HF)subpopulation was comprised of non-DR cells.Besides,the DR cells and their progenies were found distinct in their increased expression of drug-resistant genes.More intriguingly,by using the FGNP-based FACS assay to detect DR/non-DR phenotypes,we found that the DR phenotype had a potential to differentiate into the non-DR progeny,which demonstrates the differentiation feature of stem-like cancer cells.Further research disclosed that the assay can quantitatively detect the degree of drug resistance in DR cells,as well as the reversal of drug resistance that are tackled by various therapeutic methods.The strategy thus paves the way to develop theranostic approaches associated with chemotherapy-resistance and cancer stemness.展开更多
基金supported by National Natural Science Foundation of China(No.61273339)
文摘In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression features is proposed with its objective to describe features in an effective and efficient way in order to improve the recognition performance. The method combines the facial action coding system(FACS) and 'uniform' local binary patterns(LBP) to represent facial expression features from coarse to fine. The facial feature regions are extracted by active shape models(ASM) based on FACS to obtain the gray-level texture. Then, LBP is used to represent expression features for enhancing the discriminant. A facial expression recognition system is developed based on this feature extraction method by using K nearest neighborhood(K-NN) classifier to recognize facial expressions. Finally, experiments are carried out to evaluate this feature extraction method. The significance of removing the unrelated facial regions and enhancing the discrimination ability of expression features in the recognition process is indicated by the results, in addition to its convenience.
文摘Editors-in-Chief Han-Ping Shi,M.D.,Ph.D.,FACS,Professor of Surgery,Oncology and Nutrition.He is the current Chairman of the Department of GI Surgery/Clinical Nutrition at Beijing Shijitan Hospital,Capital Medical University,Beijing,China.Dr.Shi received his M.D.degree at the School of Medicine,Wuhan University,Wuhan,and his Ph.D.degree at the Second Military Medical University,Shanghai,China.From 1999 to 2002,Dr.Shi was a postdoc fellow in School of Medicine,Johns Hopkins University,under the supervision of Adrian Barbul,M.D.,FACS,and then in New Jersey Medical School,Rutgers University,under the supervision of Edwin A.Deitch,M.D.,FACS.Dr.Han-ping Shi was the Chairman of the Chinese Society for Parenteral&Enteral Nutrition(CSPEN)between 2018-2021.He is the founder Chairman of the Chinese Society of Nutritional Oncology since 2012,and the director of the Department of Academic,China Anti-Cancer Association(CACA)since 2017.Dr.Han-Ping Shi is currently the founder Editor-in-Chief of Electronic Journal of Metabolism and Nutrition of Cancer(Chinese),founder Editor-in-Chief of Journal of Nutritional Oncology(English)and founder Editor-in-Chief of Precision Nutrition(English).He is also the Associate Editor of Clinical Nutrition,Clinical Nutrition ESPEN,and Journal of Cachexia,Sarcopenia and Muscle,and Nutrition.In 2021 and 2022,he was elected as the top fi ve(second)scholars in the fi eld of nutrition in the whole world by Healsan Consulting,USA.Dr.Han-Ping Shi has published more than 500 academic papers in peer-reviewed Chinese and English journals,and presented more than 1,000 invited talks globally.Dr.Shi was the Editor-in-Chief for 27 books,and he contributed in 53 chapters in 53 books.
基金supported by the National Natural Science Foundation of China(Nos.21871180 and 81872121)the“Shuguang Program”supported by the Shanghai Education Development Foundation and the Shanghai Municipal Education Commission(No.17SG12)+2 种基金the Program for Professor of Special Appointment(Eastern Scholar)at Shanghai Institutions of Higher Learning(No.SHDP201802)the Science and Technology Commission of Shanghai Municipality(No.18520710300 and 17ZR1404100)the Biomedical Interdisciplinary Research Foundation of SJTU(No.YG2019QNB34).
文摘Herein we develop a unique differentiated-uptake strategy capable of efficient and high-purity isolation of genuine drug-resistant(DR)cells from three types of drug-surviving cancer cells,which include paclitaxel-surviving human ovarian OVCAR-3 cancer cells and human lung carcinoma A549/Taxol cells,and doxorubicin-surviving human immortalized myelogenous leukemia K562/ADR cells.By using this strategy which relies on fluorescent glycan nanoparticle(FGNP)-based fluorescence-activated cell sorting(FACS)assays,two subpopulations with distinct fluorescences existing in drug-surviving OVCAR-3 cells were separated,and we found that the lower fluorescence(LF)subpopulation consisted of DR cells,while the higher fluorescence(HF)subpopulation was comprised of non-DR cells.Besides,the DR cells and their progenies were found distinct in their increased expression of drug-resistant genes.More intriguingly,by using the FGNP-based FACS assay to detect DR/non-DR phenotypes,we found that the DR phenotype had a potential to differentiate into the non-DR progeny,which demonstrates the differentiation feature of stem-like cancer cells.Further research disclosed that the assay can quantitatively detect the degree of drug resistance in DR cells,as well as the reversal of drug resistance that are tackled by various therapeutic methods.The strategy thus paves the way to develop theranostic approaches associated with chemotherapy-resistance and cancer stemness.
