Enhancing face matching in a suitable binary environment

Abstract

Computerized human face recognition is a complex task of deformable pattern recognition. The principal source of complexities lies in the significant inter-class overlapping of faces due to the variations caused by different poses, illuminations, and expressions (PIE). The popularly used computerized face recognition algorithms like PCA, EBGM etc. are fairly reliable to determine facial attributes from an image. But, in most of the cases the features are extracted in terms of gray textures. When the database size is tuned to millions, then huge processing time is required, as each of the pixel must be represented using at least eight bits. In the present paper, our objective is to minimize the processing time by reducing the number of bits to represent each pixel. This we have done by combining two methods. The first one is a neuro-visually inspired method of figure-ground segregation (NFGS) which can convert the entire face image into a binary 2D array, efficiently. The second one is the scale invariant feature transform (SIFT) which extracts the scale invariant and rotation invariant features from the binarized face image and thereafter matches the features. The proposed algorithm is found successful in actually enhancing the performance of face matching. Psycho-visual experiments also corroborate the fact.

M2BMT: An Automated Ground Truth Generation Algorithm for Lane Detection

“…The present paper proposes an enhancement of the ground truth detection of automated lane detection system. The figure-ground segregation is mostly domain specific and researchers have tried to address the issue of identification of suitable figure from psycho-visual perspective [2] [3]. The current work proposes a new algorithm of domain specific figureground segregation on the time-sliced image constructed for each slice of row stacked from different time frames [1] [4].…”

“…This of the camera mounted on a vehicle, the variation is two way: the lane intensity profile and environmental illumination profile. Hence the state of art algorithms of figure ground segregation including cluster based algorithm like Otsu's algorithm [2] and psycho-visually inspired algorithm like NFGS [2] [3] also failed to address this specific scenario in a convincing way. As we understand from the previous section that this stage of binarization or figure-ground segregation is the heart of the complete algorithm because the automatized ground truth marking would be done in the figure extracted image from the gray intensity matrix.…”

Secure and efficient integration of big data for multi‐cells based on micro images

“…The most efficient tracing algorithm is the Scale Invariant Feature Transform (SIFT) [1][2][3] algorithm by far. SIFT was introduced by David Lowe, which can match the same objects in the different images using the extracted invariant feature from images.…”