首页|Chouaib Doukkali University Researcher Reports on Findings in Machine Learning ( A Mighty Image Retrieval Descriptor Based on Machine Learning and Gaussian Deriv ative Filter)
Chouaib Doukkali University Researcher Reports on Findings in Machine Learning ( A Mighty Image Retrieval Descriptor Based on Machine Learning and Gaussian Deriv ative Filter)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A new study on artificial intelligence is now ava ilable. According to news reporting out of Chouaib Doukkali University by NewsRx editors, research stated, “The development of new image descriptor has always b een an important topic to improve the efficiency of content- based image classif ication and retrieval.” The news correspondents obtained a quote from the research from Chouaib Doukkali University: “Improvements and developments in machine learning and deep learnin g algorithms as well as artificial intelligence algorithms are widely used by re searchers to obtain effective CBIR descriptors. In our article, we will present a robust image descriptor, extended by machine learning and deep learning algori thms. The descriptor is provided through a Gaussian derivative filter scaffold n amed GDF-HOG with an enhanced convolutional neural network (CNN) AlexNet, to red uce the dimensions we used the principal component analysis algorithm. The exper imental results were carried out on Oliva and Torralba, Caltech-101, Wang and Co il100 datasets. Experiments show that the accuracy of the proposed method is 98. 23% for Coil-100 %, 95.92% for Corel-100 0, value 87.17 and 94.6% for Oliva and Torralba.”
NETL
NSTL
