In this paper, we introduce BoSP (Bonn Salient Points), a method comprising a pair of a keypoint detector and descriptor in image data that are deeply geared to one another. Our detector identifies points of interest to be local maxima of appearance contrast to their surroundings in a statistical manner. This criterion admits a selection of particularly repeatable, but diverse looking keypoints...

Introduction. Recently, a comparative study in [2] has shown the superior performance of local features for face recognition in unconstrained environments. Due to the global integration of Speeded Up Robust Features (SURF) [1], the authors claim that it stays more robust to various image perturbations than the more locally operating SIFT descriptor. However, no detailed analysis for a SURF base...

Recent methods for learning similarity between images have presented impressive results in the problem of pair matching (same/notsame classification) of face images. In this paper we explore how well this performance carries over to the related task of multi-option face identification, specifically on the Labeled Faces in the Wild (LFW) image set. In addition, we seek to compare the performance...

In this project, the task of architecture classification for monuments and buildings from the Indian subcontinent was explored. Five major classes of architecture were taken and various supervised learning methods, both probabilistic and nonprobabilistic, were experimented with in order to classify the monuments into one of the five categories. The categories were: ’Ancient’, ’British’, ’IndoIs...

Object recognition is an important problem in computer vision, having diverse applications. In this work, we construct an end-to-end scene recognition pipeline consisting of feature extraction, encoding, pooling and classification. Our approach simultaneously utilize global feature descriptors as well as local feature descriptors from images, to form a hybrid feature descriptor corresponding to...

Numerous researchers have used machine vision in recent years to identify and categorize clouds according their volume, shape, thickness, height, coverage. Due the significant variations illumination, climate, distortion that frequently characterize cloud images as a type of naturally striated structure, Local Binary Patterns (LBP) descriptor its variants been proposed feature extraction method...

Impression from the fingers and its matching is one of the important task of law enforcing body. Minutia extraction from the fingerprint image decides the accuracy of the matching. Method presented in this paper is also very efficient in matching the algorithm. Minutia cylindrical code(MCC) which is local descriptor of the fingerprint image is used for matching the fingerprint image. MCC, codes...

Image descriptor performs two major tasks of the extracting algorithm. One is to encode image into feature vectors and the other is to measure for comparing a query image and the images in database. This paper proposes a new efficient image descriptor that uses the color feature based on wavelet color-spatial information of an image. In order to evaluate the proposed descriptor, we perform the ...