Pub Date : 2023-03-01DOI: 10.18178/joig.11.1.82-90
Amarpreet Singh, Sanjogdeep Singh
With advancement in technology, especially in imaging field, digital image forgery has increased a lot nowadays. In order to counter this problem, many forgery detection techniques have been developed from time to time. For rapid and accurate detection of forged image, a novel hybrid technique is used in this research work that implements Gray Level Co-occurrence Matrix (GLCM) along with Binary Robust Invariant Scalable Keypoints (BRISK). GLCM significantly extracts key attributes from an image efficiently which will help to increase the detection accuracy. BRISK is known to be one of the 3 fastest modes of detection which will increase the execution speed of GLCM. BRISK even processes scaled and rotated images. Then the Principal Component Analysis (PCA) algorithm is applied in the final phase of detection will remove any unrequited element from the scene and highlights the concerned forged area.
{"title":"Gray Level Co-occurrence Matrix with Binary Robust Invariant Scalable Keypoints for Detecting Copy Move Forgeries","authors":"Amarpreet Singh, Sanjogdeep Singh","doi":"10.18178/joig.11.1.82-90","DOIUrl":"https://doi.org/10.18178/joig.11.1.82-90","url":null,"abstract":"With advancement in technology, especially in imaging field, digital image forgery has increased a lot nowadays. In order to counter this problem, many forgery detection techniques have been developed from time to time. For rapid and accurate detection of forged image, a novel hybrid technique is used in this research work that implements Gray Level Co-occurrence Matrix (GLCM) along with Binary Robust Invariant Scalable Keypoints (BRISK). GLCM significantly extracts key attributes from an image efficiently which will help to increase the detection accuracy. BRISK is known to be one of the 3 fastest modes of detection which will increase the execution speed of GLCM. BRISK even processes scaled and rotated images. Then the Principal Component Analysis (PCA) algorithm is applied in the final phase of detection will remove any unrequited element from the scene and highlights the concerned forged area.","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75036383","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}
Lin Jiang, Yifeng Zheng, Chen Che, Li Guohe, Wenjie Zhang
： Deep learning technique has been developing intensively in big data era. However ， its capability is still chal⁃ lenged for the design of network structure and parameter setting. Therefore ， it is essential to improve the performance of the model and optimize the complexity of the model. Machine learning can be segmented into five categories in terms of learn⁃ ing methods ： 1 ） supervised learning ， 2 ） unsupervised learning ， 3 ） semi - supervised learning ， 4 ） deep learning ， and 5 ） reinforcement learning. These machine learning techniques are required to be incorporated in. To improve its fitting and
{"title":"Review of optimization methods for supervised deep learning","authors":"Lin Jiang, Yifeng Zheng, Chen Che, Li Guohe, Wenjie Zhang","doi":"10.11834/jig.211139","DOIUrl":"https://doi.org/10.11834/jig.211139","url":null,"abstract":"： Deep learning technique has been developing intensively in big data era. However ， its capability is still chal⁃ lenged for the design of network structure and parameter setting. Therefore ， it is essential to improve the performance of the model and optimize the complexity of the model. Machine learning can be segmented into five categories in terms of learn⁃ ing methods ： 1 ） supervised learning ， 2 ） unsupervised learning ， 3 ） semi - supervised learning ， 4 ） deep learning ， and 5 ） reinforcement learning. These machine learning techniques are required to be incorporated in. To improve its fitting and","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80080636","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}
{"title":"Temporal series features extraction based on Bi-ConvLSTM of Alzheimer’s disease pridiction CTISS model","authors":"Hong Xin, Kaifeng Huang, Chenhui Yang","doi":"10.11834/jig.211186","DOIUrl":"https://doi.org/10.11834/jig.211186","url":null,"abstract":"","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81878764","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}
Xu Jiangtao, Wang Xinyang, Wang Tingdong, Chen Xin, Song Zongxi, Lei Hao, Liu Gang, Wen Desheng
{"title":"Review on optical visual sensor technology","authors":"Xu Jiangtao, Wang Xinyang, Wang Tingdong, Chen Xin, Song Zongxi, Lei Hao, Liu Gang, Wen Desheng","doi":"10.11834/jig.230039","DOIUrl":"https://doi.org/10.11834/jig.230039","url":null,"abstract":"","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73306483","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}
Yunpeng Liu, Tielin Wu, Cai Wenli, Renfang Wang, Dechao Sun, Kaifeng Gan, Li Jin, Jin Ran, Qiu Hong, Huixia Xu
{"title":"Pre analysis of difficulty in renal tumor enucleation surgery based on deep learning and image automation evaluation","authors":"Yunpeng Liu, Tielin Wu, Cai Wenli, Renfang Wang, Dechao Sun, Kaifeng Gan, Li Jin, Jin Ran, Qiu Hong, Huixia Xu","doi":"10.11834/jig.220375","DOIUrl":"https://doi.org/10.11834/jig.220375","url":null,"abstract":"","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89224199","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}
Jiafei Liang, Li Ting, Yang Jiaqi, Li Yanan, Zhiwen Fang, Yang Feng
： Objective Anomaly detection has been developing in video surveillance domain. Video anomaly detection is
客观异常检测是视频监控领域的发展方向。视频异常检测
{"title":"Video anomaly detection by fusing self-attention and autoencoder","authors":"Jiafei Liang, Li Ting, Yang Jiaqi, Li Yanan, Zhiwen Fang, Yang Feng","doi":"10.11834/jig.211147","DOIUrl":"https://doi.org/10.11834/jig.211147","url":null,"abstract":"： Objective Anomaly detection has been developing in video surveillance domain. Video anomaly detection is","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79602862","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}
{"title":"Research on visual analysis methods of bird satellite tracking data： a case study analysis for Nipponia nippon","authors":"Xinyue Li, Jiang Xian, Weiqun Cao, Dongping Liu","doi":"10.11834/jig.220403","DOIUrl":"https://doi.org/10.11834/jig.220403","url":null,"abstract":"","PeriodicalId":36336,"journal":{"name":"中国图象图形学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85350443","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：