An Intelligent system to estimate and classify the agricul-tural and food products using coloring local features

Narendra, V G and Pinto, Ancilla Juliet (2018) An Intelligent system to estimate and classify the agricul-tural and food products using coloring local features. International Journal of Engineering and Technology(UAE), 7 (4). pp. 4246-4249. ISSN 2227-524X

[img] PDF
5639.pdf - Published Version
Restricted to Registered users only

Download (331kB) | Request a copy


Color is commonly perceived as an indispensable quality in describing edible nuts, fruits, vegetables and food grains. State-of-the art local feature-based representations are mostly based on shape description, and ignore color information. The measured color values vary significantly due to large amount of variations which in turn hamper the description of color. The aim of this paper is to extend the de-scription of local features of images of agricultural and food products with color information. To accomplish a wide applicability of the color descriptor, it should be robust to the photometric changes that are commonly encountered in the images of agricultural and food products and also the varying image quality ranging from high quality images to snap-shot photo quality and compressed images. Based on these requirements we derive a set of color descriptors. The set of proposed descriptors are compared by extensive testing on agricul-tural and food products images, namely, matching, retrieval and classification and on wide variety of image qualities. The results show that the color descriptors remain reliable under photometric and geometrical changes, and also for poor image quality. For all the experi-ments carried out, it is observed that a combination of color and shape based–approach outperforms a pure shape-based approach.

Item Type: Article
Uncontrolled Keywords: Agricultural and food products images, Classification, Matching, Local features.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 05 Jan 2019 06:19
Last Modified: 05 Jan 2019 06:19

Actions (login required)

View Item View Item