Title of talk: Co-occurrence based Local Pattern for Content based Image Retrieval

Abstract: Content-based image retrieval (CBIR) is the application of computer vision techniques and it involves the problem of searching for digital images in large databases. CBIR has been a popular research area due to extensive online and offline image database. Feature extraction and similarity detection are measure aspects of a CBIR system. Local patterns have proved their excellence in extracting texture features from the image. In this talk, I shall present co-occurrence based local pattern for content based image retrieval using center symmetric local binary pattern (CSLBP) and gray level co-occurrence matrix (GLCM). The proposed feature descriptor extracts deep texture information based on co-occurrence of pixel pairs in local pattern map of image. Finally, I will present extensive experiments on textural, medical and facial image datasets.


Dr. Manisha Verma
Short Bio: Manisha Verma has completed her Ph.D. from Mathematics Department, Indian Institute of Technology Roorkee, Roorkee, India in April, 2016. She has received M.Sc. degree in Industrial Mathematics and Informatics from Mathematics Department, Indian Institute of Technology Roorkee, Roorkee, India in 2012, the B.Sc. degree from Maharani’s college, Rajasthan University, Jaipur, India in 2009. Her area of interest include feature extraction, content based image retrieval, biometric verification and recognition, video shot boundary detection and keyframe extraction and text detection in images and videos.