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

by   Ravimal Bandara, et al.

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.



There are no comments yet.


page 8

page 9

page 11


A New Color Feature Extraction Method Based on Dynamic Color Distribution Entropy of Neighborhoods

One of the important requirements in image retrieval, indexing, classifi...

Frost filtered scale-invariant feature extraction and multilayer perceptron for hyperspectral image classification

Hyperspectral image (HSI) classification plays a significant in the fiel...

Indoor image representation by high-level semantic features

Indoor image features extraction is a fundamental problem in multiple fi...

M-ar-K-Fast Independent Component Analysis

This study presents the m-arcsinh Kernel ('m-ar-K') Fast Independent Com...

Nonnegative OPLS for Supervised Design of Filter Banks: Application to Image and Audio Feature Extraction

Audio or visual data analysis tasks usually have to deal with high-dimen...

Supervised learning for crop/weed classification based on color and texture features

Computer vision techniques have attracted a great interest in precision ...

Hardware based Scale- and Rotation-Invariant Feature Extraction: A Retrospective Analysis and Future Directions

Computer Vision techniques represent a class of algorithms that are high...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.