Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction

Fast and invariant feature extraction is crucial in certain computer vision applications where the computation time is constrained in both training and testing phases of the classifier. In this paper, we propose a nature-inspired dimensionality reduction technique for fast and invariant visual feature extraction. The human brain can exchange the spatial and spectral resolution to reconstruct missing colors in visual perception. The phenomenon is widely used in the printing industry to reduce the number of colors used to print, through a technique, called color dithering. In this work, we adopt a fast error-diffusion color dithering algorithm to reduce the spectral resolution and extract salient features by employing novel Hessian matrix analysis technique, which is then described by a spatial-chromatic histogram. The computation time, descriptor dimensionality and classification performance of the proposed feature are assessed under drastic variances in orientation, viewing angle and illumination of objects comparing with several different state-of-the-art handcrafted and deep-learned features. Extensive experiments on two publicly available object datasets, coil-100 and ALOI carried on both a desktop PC and a Raspberry Pi device show multiple advantages of using the proposed approach, such as the lower computation time, high robustness, and comparable classification accuracy under weakly supervised environment. Further, it showed the capability of operating solely inside a conventional SoC device utilizing a small fraction of the available hardware resources.

Image Segmentation using Unsupervised Watershed Algorithm with an Over-segmentation Reduction Technique

Image segmentation is the process of partitioning an image into meaningful segments. The meaning of the segments is subjective due to the definition of homogeneity is varied based on the users perspective hence the automation of the segmentation is challenging. Watershed is a popular segmentation technique which assumes topographic map in an image, with the brightness of each pixel representing its height, and finds the lines that run along the tops of ridges. The results from the algorithm typically suffer from over segmentation due to the lack of knowledge of the objects being classified. This paper presents an approach to reduce the over segmentation of watershed algorithm by assuming that the different adjacent segments of an object have similar color distribution. The approach demonstrates an improvement over conventional watershed algorithm.