Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266560
Shotaro Sakurai, Seiya Takigami, Takashi Ida, Yuki Ozawa, N. Tsukiji, Y. Kobori, Haruo Kobayashi, Ryoji Shiota
This paper describes a general equation of the input and output relation in N-stage configuration of a trigger circuit, which outputs a sine wave (or a cosine wave) with a zero phase at the timing when a trigger signal input is applied. Its conventional configuration employs two or three stages of a track hold circuit and an analog multiplier with some glue circuits, and it is targeted for a digital oscilloscope. Our N-stage trigger circuit can average non-ideal characteristics of each phase with N stages, and it is expected that a high precision trigger circuit can be realized. This may lead to analog circuit realization with low supply voltage; in other words, each analog circuit is not precise but the whole trigger circuit is precise. Also, its application as a pre-stage of the successive approximation time-to-digital converter for one-shot timing measurement is proposed.
{"title":"Study of multistage digital oscilloscope trigger circuit","authors":"Shotaro Sakurai, Seiya Takigami, Takashi Ida, Yuki Ozawa, N. Tsukiji, Y. Kobori, Haruo Kobayashi, Ryoji Shiota","doi":"10.1109/ISPACS.2017.8266560","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266560","url":null,"abstract":"This paper describes a general equation of the input and output relation in N-stage configuration of a trigger circuit, which outputs a sine wave (or a cosine wave) with a zero phase at the timing when a trigger signal input is applied. Its conventional configuration employs two or three stages of a track hold circuit and an analog multiplier with some glue circuits, and it is targeted for a digital oscilloscope. Our N-stage trigger circuit can average non-ideal characteristics of each phase with N stages, and it is expected that a high precision trigger circuit can be realized. This may lead to analog circuit realization with low supply voltage; in other words, each analog circuit is not precise but the whole trigger circuit is precise. Also, its application as a pre-stage of the successive approximation time-to-digital converter for one-shot timing measurement is proposed.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121310074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266489
Haoyuan Ma, Gaoyun An, Shengjie Wu, Feng Yang
Micro-expressions are the momentary facial expressions that reveal genuine emotional state of people. However, the detection and recognition of micro-expression have been greatly challenging. The apex frame which indicates the most expressive state of a micro-expression will be very helpful for further research on micro-expression. But labeling the apex frame manually is very time-consuming. In this paper, we propose a novel Region Histogram of Oriented Optical Flow (RHOOF) feature to spot the apex frame automatically. First, a set of facial landmarks are detected and then 5 Regions Of Interest (ROIs) are selected from facial region based on the frequency of occurrence of action units. Finally, we extract optical flow fields frame-by-frame and compute HOOF in these ROIs. Experiments are conducted on two ideal spontaneous micro-expression databases, i.e., CASME and CASME II. Improvements of 30.77% and 19.04% are achieved respectively in CASME and CASME II when compared to the BS-RoIs.
{"title":"A Region Histogram of Oriented Optical Flow (RHOOF) feature for apex frame spotting in micro-expression","authors":"Haoyuan Ma, Gaoyun An, Shengjie Wu, Feng Yang","doi":"10.1109/ISPACS.2017.8266489","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266489","url":null,"abstract":"Micro-expressions are the momentary facial expressions that reveal genuine emotional state of people. However, the detection and recognition of micro-expression have been greatly challenging. The apex frame which indicates the most expressive state of a micro-expression will be very helpful for further research on micro-expression. But labeling the apex frame manually is very time-consuming. In this paper, we propose a novel Region Histogram of Oriented Optical Flow (RHOOF) feature to spot the apex frame automatically. First, a set of facial landmarks are detected and then 5 Regions Of Interest (ROIs) are selected from facial region based on the frequency of occurrence of action units. Finally, we extract optical flow fields frame-by-frame and compute HOOF in these ROIs. Experiments are conducted on two ideal spontaneous micro-expression databases, i.e., CASME and CASME II. Improvements of 30.77% and 19.04% are achieved respectively in CASME and CASME II when compared to the BS-RoIs.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126530751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266506
Tian Sun, Ao Peng, Biyu Tang, Lingxiang Zheng, Hao Li, G. Ou
In Wi-Fi fingerprinting localization system, good positioning accuracy requires accurate fingerprint database, but too much heavy labor was involved in the collection of accurate fingerprint. Therefore, the collection, calibration and maintenance of fingerprint database in Wi-Fi positioning has always been one of the research hotspots. In this paper, a parameterized fingerprint construction system is proposed to obtain an accurate fingerprint database, and the collection and periodic maintenance of fingerprints is relatively efficient. In the proposed scheme, Wi-Fi signal collected in actual environment and wireless signal propagation theory is used to model APs in the interested area by using the least squares fitting method to construct a fingerprint database which matches the surrounding environment. At the end of the paper, an experiment was carried out at Haiyun teaching building of Xiamen University. Compared with the original fingerprints, the positioning accuracy of optimized fingerprints obtained by the proposed scheme is improved by 48%.
{"title":"A parameterized wifi fingerprint database construction method","authors":"Tian Sun, Ao Peng, Biyu Tang, Lingxiang Zheng, Hao Li, G. Ou","doi":"10.1109/ISPACS.2017.8266506","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266506","url":null,"abstract":"In Wi-Fi fingerprinting localization system, good positioning accuracy requires accurate fingerprint database, but too much heavy labor was involved in the collection of accurate fingerprint. Therefore, the collection, calibration and maintenance of fingerprint database in Wi-Fi positioning has always been one of the research hotspots. In this paper, a parameterized fingerprint construction system is proposed to obtain an accurate fingerprint database, and the collection and periodic maintenance of fingerprints is relatively efficient. In the proposed scheme, Wi-Fi signal collected in actual environment and wireless signal propagation theory is used to model APs in the interested area by using the least squares fitting method to construct a fingerprint database which matches the surrounding environment. At the end of the paper, an experiment was carried out at Haiyun teaching building of Xiamen University. Compared with the original fingerprints, the positioning accuracy of optimized fingerprints obtained by the proposed scheme is improved by 48%.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127407157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266469
J. Chen, Jie Liao, H. Zeng, C. Cai
To meet the requirement of robust multi-view video transmission through error prone channels, a multi-view multiple description video coding scheme with adaptive redundancy allocation strategy is proposed in this paper. The redundancy of the codec can be adaptively adjusted according to different packet loss circumstances of the network. The effectiveness and robustness of the proposed multiple description coding scheme for multi-view video is verified by experiments on the JMVC coding platform.
{"title":"Multiple description coding for multi-view video with adaptive redundancy allocation","authors":"J. Chen, Jie Liao, H. Zeng, C. Cai","doi":"10.1109/ISPACS.2017.8266469","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266469","url":null,"abstract":"To meet the requirement of robust multi-view video transmission through error prone channels, a multi-view multiple description video coding scheme with adaptive redundancy allocation strategy is proposed in this paper. The redundancy of the codec can be adaptively adjusted according to different packet loss circumstances of the network. The effectiveness and robustness of the proposed multiple description coding scheme for multi-view video is verified by experiments on the JMVC coding platform.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126886509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266454
Shangxin Lin, Hua Shen, Zhili Lin, Lu Lin, Ze Dong
A probabilistic shaping modulation (PSM) format based on fixed-to-fixed (f2f) symbols projection constant composition distribution matching (SP-CCDM) method is proposed. The proposed PSM is an eminent coding method since the optimized redundancy rate by SP-CCDM is smaller than the one with conventional CCDM method. The change of constellation diagram under representative signal noise ratio rationalizes the root to corrupted signals during the investigation of spectral efficiency. The f2f SP-CCDM method offers an effective way to purification of received signals.
{"title":"Dynamic probabilistic shaping modulation based on fixed-to-fixed symbols projection constant composition distribution matching","authors":"Shangxin Lin, Hua Shen, Zhili Lin, Lu Lin, Ze Dong","doi":"10.1109/ISPACS.2017.8266454","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266454","url":null,"abstract":"A probabilistic shaping modulation (PSM) format based on fixed-to-fixed (f2f) symbols projection constant composition distribution matching (SP-CCDM) method is proposed. The proposed PSM is an eminent coding method since the optimized redundancy rate by SP-CCDM is smaller than the one with conventional CCDM method. The change of constellation diagram under representative signal noise ratio rationalizes the root to corrupted signals during the investigation of spectral efficiency. The f2f SP-CCDM method offers an effective way to purification of received signals.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132033276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266605
T. Adiono, Hans Ega, Hans Kasan, S. Fuada, S. Harimurti
The asymmetric RSA cryptosystem requires modulo operations in its encryption and decryption process, which is often realized with Montgomery modular multiplication. In this paper, we proposed a Montgomery multiplier hardware design using only primitive gates, adders, shifters, multiplexers, and registers. Our algorithm is also adaptable, which means that it can be reconfigured for applications with any arbitrary bits. The algorithm involves iteration, and to achieve less transistor count, we realized the iteration by feeding back the calculation results at the output back to the input, instead of connecting the gates in series. These considerations are made to allow us to create a compact custom ASIC design. The design was made with 130nm standard CMOS technology with NMOS and PMOS base width of 0.5|jm and 1 urn respectively. With the algorithm, our 8-bit multiplier ASIC design occupies an area of 0.0266mm2. The design is created and verified with Mentor Graphics™ EDA tools.
{"title":"Full custom design of adaptable montgomery modular multiplier for asymmetric RSA cryptosystem","authors":"T. Adiono, Hans Ega, Hans Kasan, S. Fuada, S. Harimurti","doi":"10.1109/ISPACS.2017.8266605","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266605","url":null,"abstract":"The asymmetric RSA cryptosystem requires modulo operations in its encryption and decryption process, which is often realized with Montgomery modular multiplication. In this paper, we proposed a Montgomery multiplier hardware design using only primitive gates, adders, shifters, multiplexers, and registers. Our algorithm is also adaptable, which means that it can be reconfigured for applications with any arbitrary bits. The algorithm involves iteration, and to achieve less transistor count, we realized the iteration by feeding back the calculation results at the output back to the input, instead of connecting the gates in series. These considerations are made to allow us to create a compact custom ASIC design. The design was made with 130nm standard CMOS technology with NMOS and PMOS base width of 0.5|jm and 1 urn respectively. With the algorithm, our 8-bit multiplier ASIC design occupies an area of 0.0266mm2. The design is created and verified with Mentor Graphics™ EDA tools.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130790157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266581
Yanzhu Zhang, Minghai Zhang, Yijie Liu, Fandi Wang
When processing the image, The first-order image de-fuzzification template which is defined by the traditional integer differential produces a wide edge, while the second-order template enhances texture and noise. In order to avoid the side effects of the integer differential template, this paper constructs the fractional differential mask and constructs the fractional differential mask, In the traditional fractional mask, by setting the parameters manually, the entropy of the image can be used to determine the abundance of the image information as an image test standard, and an entropy optimal fractional differential mask parameter is selected, The simulation results show that the mask can not only keep the low-frequency contour information of the smooth region, but also enhance the texture information of the high-frequency edge and high-frequency in the image. For the severe weather images, the method used in this paper has a good effect, can retain the image information very well.
{"title":"A fractional-order optimization and parametric selection method of fractional differential masks","authors":"Yanzhu Zhang, Minghai Zhang, Yijie Liu, Fandi Wang","doi":"10.1109/ISPACS.2017.8266581","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266581","url":null,"abstract":"When processing the image, The first-order image de-fuzzification template which is defined by the traditional integer differential produces a wide edge, while the second-order template enhances texture and noise. In order to avoid the side effects of the integer differential template, this paper constructs the fractional differential mask and constructs the fractional differential mask, In the traditional fractional mask, by setting the parameters manually, the entropy of the image can be used to determine the abundance of the image information as an image test standard, and an entropy optimal fractional differential mask parameter is selected, The simulation results show that the mask can not only keep the low-frequency contour information of the smooth region, but also enhance the texture information of the high-frequency edge and high-frequency in the image. For the severe weather images, the method used in this paper has a good effect, can retain the image information very well.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124218288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266479
Fengyong Li, Mingquan Xin, Jinguo Li, Jiang Yu
This work proposes an improvement solution for detecting copy-move forgery in individual image. The proposed method can significantly remove a large number of uncombined image block by using multi-scale sliding windows, so, it is different from the existing schemes. The proposed scheme consists of feature extraction, feature matching and uncombined block removing. DCT coefficient are extracted to design low-dimensional features which are considered to be more sensitive to copy region of image. Furthermore, we use fast k-means method to integrate image blocks with similar features as different clusters. Finally, multi-scale sliding windows is designed to further remove the uncombined blocks in detection results. Extensive experiments show that the proposed scheme is effective and efficient and outperforms the state-of-the-art copy-move detection methods with a lower false positive rate.
{"title":"Improved detection for copy-move forgery with multi-scale sliding windows","authors":"Fengyong Li, Mingquan Xin, Jinguo Li, Jiang Yu","doi":"10.1109/ISPACS.2017.8266479","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266479","url":null,"abstract":"This work proposes an improvement solution for detecting copy-move forgery in individual image. The proposed method can significantly remove a large number of uncombined image block by using multi-scale sliding windows, so, it is different from the existing schemes. The proposed scheme consists of feature extraction, feature matching and uncombined block removing. DCT coefficient are extracted to design low-dimensional features which are considered to be more sensitive to copy region of image. Furthermore, we use fast k-means method to integrate image blocks with similar features as different clusters. Finally, multi-scale sliding windows is designed to further remove the uncombined blocks in detection results. Extensive experiments show that the proposed scheme is effective and efficient and outperforms the state-of-the-art copy-move detection methods with a lower false positive rate.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123436797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266589
Hailian Yu, Hairong Wang, Chen Liu
The purpose of this paper is to minimize total of the consumed power while making sure users can reach desired achievable rates in multi cell multi user massive multiple input multiple output (MIMO) system. The setting of CoBF (the coordinated beamforming scheme) in which each user receives useful signal from its own cell but treat signal from other cells as interference is considered. First, expressions of the downlink (DL) achievable user rates by taking maximum ratio transmission (MRT) precoding and zero-forcing (ZF) precoding into consideration are derived. Based on those expressions, the DL power minimization problem is presented, to solve this problem, linear programming is used. Further, the problem of finding appropriate achievable rate target by using max-min achievable rate algorithm is solved. Numerical results show effectiveness of our proposed method.
{"title":"The analysis of power allocation of base station cooperation in massive MIMO","authors":"Hailian Yu, Hairong Wang, Chen Liu","doi":"10.1109/ISPACS.2017.8266589","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266589","url":null,"abstract":"The purpose of this paper is to minimize total of the consumed power while making sure users can reach desired achievable rates in multi cell multi user massive multiple input multiple output (MIMO) system. The setting of CoBF (the coordinated beamforming scheme) in which each user receives useful signal from its own cell but treat signal from other cells as interference is considered. First, expressions of the downlink (DL) achievable user rates by taking maximum ratio transmission (MRT) precoding and zero-forcing (ZF) precoding into consideration are derived. Based on those expressions, the DL power minimization problem is presented, to solve this problem, linear programming is used. Further, the problem of finding appropriate achievable rate target by using max-min achievable rate algorithm is solved. Numerical results show effectiveness of our proposed method.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121043496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ISPACS.2017.8266484
Tao Wu, Xin Li, Bing Wang, Jier Yu, Pengcheng Li, Shanqing Zhang
Hologram label can present different images under different light condition. Thus, it is difficult to recognize a hologram label with traditional methods. In this paper, we propose a classification algorithm for hologram label based on improved SIFT features. Firstly, a multi-illumination sample space is constructed by collecting images from one hologram label under different illumination condition. Secondly, the SIFT features are extracted from different samples in the multi-illumination sample space. Thirdly, some stable feature points are obtained after matching and clustering steps. Finally, the class of a testing hologram label is determined by the number of the matched SIFT points. Experimental results show that our method has good accuracy and recall rate, especially the ambiguous images can also be recognized.
{"title":"A classification algorithm for hologram label based on improved sift features","authors":"Tao Wu, Xin Li, Bing Wang, Jier Yu, Pengcheng Li, Shanqing Zhang","doi":"10.1109/ISPACS.2017.8266484","DOIUrl":"https://doi.org/10.1109/ISPACS.2017.8266484","url":null,"abstract":"Hologram label can present different images under different light condition. Thus, it is difficult to recognize a hologram label with traditional methods. In this paper, we propose a classification algorithm for hologram label based on improved SIFT features. Firstly, a multi-illumination sample space is constructed by collecting images from one hologram label under different illumination condition. Secondly, the SIFT features are extracted from different samples in the multi-illumination sample space. Thirdly, some stable feature points are obtained after matching and clustering steps. Finally, the class of a testing hologram label is determined by the number of the matched SIFT points. Experimental results show that our method has good accuracy and recall rate, especially the ambiguous images can also be recognized.","PeriodicalId":166414,"journal":{"name":"2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122777967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：