Direct Edge Alignment (D-EA)

Abstract There has been a paradigm shifting trend towards feature-less methods due to their elegant formulation, accuracy and ever increasing computational power. In this work, we present a direct edge alignment approach for 6-DOF tracking. We argue that photo-consistency based methods are plagued by a much smaller convergence basin and are extremely sensitive to noise, changing illumination … Continue reading Direct Edge Alignment (D-EA)

Advertisements

Color Consistency from Multiple-View Images

Abstract In this paper we address the problem of multiview color consistency. We propose to use a graph model of 3d positions obtained using matched dense feature points. We define an energy functional on this model which captures relationship of the colors across views while also imposing a smoothness cost to obtain optimal colors for the 3d … Continue reading Color Consistency from Multiple-View Images

Detection of Mitosis in Multispectral Breast Cancer Imagery

Mitotic count is an important parameter for the prognosis of breast cancer. However, mitosis detection is a challenging problem and has not been addressed well in the literature. Indeed, mitosis detection is very challenging since mitosis appear in image as small objects with a large variety of shapes, and they can thus be confused with … Continue reading Detection of Mitosis in Multispectral Breast Cancer Imagery

AutoDBC : Scalable System for Classification of White Blood Cells from Leishman Stained Blood Stain Images

Automatic Differential Blood Count

WBC differential count yields clinically relevant information about health and disease. Currently, pathologists manually annotate the WBCs (Differential WBC Count) according to their experience and intuition which is a subjective task and therefore not perfectly reproducible. Furthermore, this work is tedious and time consuming. This study aims at automation of DBC process so as to increase the productivity & eliminate human errors. The proposed system takes peripheral Leishman blood stain images as input and generates count of each WBC sub-type (DBC). There have been a few efforts in the past to automate the solution to this problem. In the opinion of the authors of this paper, the previous works on automation of differential WBC count have not laid emphasis on development of fast, parallel and scalable system. Such a fast system is needed as the number of DBC a pathology lab handles is enormous in number. This study focuses on…

View original post 347 more words