An Improved Artificial Bee Colony Algorithm for the Object Recognition Problem in Complex Digital Images Using Template Matching

Abstract

In this paper, the authors present an improved Artificial Bee Colony Algorithm (ABC) for the object recognition problem in complex digital images. The ABC is a new metaheuristics approach inspired by the collective foraging behavior of honey bee swarms. The objective is to find a pattern or reference image (template) of an object somewhere in a target landscape scene that may contain noise and changes in brightness and contrast. First, several search strategies were tested to find the most appropriate. Next, many experiments were done using complex digital grayscale and color images. Results are analyzed and compared with other algorithms through Pareto plots and graphs that show that the improved ABC was more efficient than the original ABC.

Multiple Face Recognition Using Local Features and Swarm Intelligence

“…Our main objective in the face recognition task is to recognize a target face image as fast as possible so that this kind of algorithm can be applied to real-world problems. In this context, the improved ABC algorithm comprises three main mechanisms that were tested in the study conducted by Chidambaram and Lopes [25]: (1) the perturbation of multiple variables; (2) generation of multiple scout bees; (3) explosion of stagnated solutions. Based on the three proposed mechanisms and the mechanisms which were already present in the basic ABC algorithm, such as the perturbation of a single variable and generation of a single scout bee using the Limit parameter, several experiments were done.…”

“…Metaheuristic optimization algorithms, such as those from the Swarm Intelligence area, were successfully applied to face recognition problems. Several optimization algorithms have been successfully applied to face recognition purposes, such as Particle Swarm Optimization (PSO) [23], [24] and Artificial Bee Colony (ABC) [25] algorithms. Face detection and recognition constitute problems in which optimization algorithms have great potential to improve detection or recognition accuracy.…”

“…For that, we propose a robust approach using SURF [9] for interest point detection and description, and an improved ABC algorithm (iABC) [25]. SURF was chosen because of its promising performance and computational efficiency [9], [30].…”

“…SURF was chosen because of its promising performance and computational efficiency [9], [30]. Similarly, iABC was chosen because it was already applied to object recognition and has proven to be an excellent optimization algorithm [25]. In addition to the search process for an optimal solution, the iABC can also determine the optimal image parameters (horizontal and vertical coordinates, rotation angle and scale).…”

Comparison of Three Evolutionary Algorithms: PSOA, ACOA and BCOA on Recognition Arabic Characters Problem

“…In Recognition system has to recognize the object such as character, number, symbol …..etc. , in defined way [1,2]. The swarm intelligent techniques are considered the most modern artificial intelligence techniques, which contains many approaches that are used to solve optimization problems with high presentation and effectiveness and appropriate behavior to solve various optimization problems such as character recognition and make a comparison among them in term of behavior and presentation.…”