Automatic Fruit and Vegetable Recognition Based on CENTRIST and Color Representation

Full text
Author(s):	Ramirez Cornejo, Jadisha Yarif ; Pedrini, Helio ; BeltranCastanon, C ; Nystrom, I ; Famili, F Total Authors: 5
Document type:	Journal article
Source:	PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2016; v. 10125, p. 8-pg., 2017-01-01.
Abstract
Automatic fruit and vegetable recognition from images is still a very challenging task. In this work, we describe and analyze an efficient and accurate fruit and vegetable recognition system based on fusing two visual descriptors: Census Transform Histogram (CENTRIST) and Hue-Saturation (HS) Histogram representation. Initially, background subtraction is applied to the fruit and vegetable images. CENTRIST and HS-Histogram are extracted, as well as Color CENTRIST features for comparison purpose. Then, the feature vector is reduced through Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). In the recognition process, K-nearest neighbor (K-NN) and Support Vector Machine (SVM) classifiers are employed. Experiments conducted on a benchmark demonstrate that combining CENTRIST and HS-Histogram representation reached high and competitive recognition accuracy rates compared to other similar works in the literature. (AU)

FAPESP's process:	11/22749-8 - Challenges in exploratory visualization of multidimensional data: paradigms, scalability and applications
Grantee:	Luis Gustavo Nonato
Support Opportunities:	Research Projects - Thematic Grants