Automated Design of Salient Object Detection Algorithms with Brain Programming

Despite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progr...

Full description

Bibliographic Details
Main Authors: Gustavo Olague, Jose Armando Menendez-Clavijo, Matthieu Olague, Arturo Ocampo, Gerardo Ibarra-Vazquez, Rocio Ochoa, Roberto Pineda
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/12/20/10686
_version_ 1797475514699481088
author Gustavo Olague
Jose Armando Menendez-Clavijo
Matthieu Olague
Arturo Ocampo
Gerardo Ibarra-Vazquez
Rocio Ochoa
Roberto Pineda
author_facet Gustavo Olague
Jose Armando Menendez-Clavijo
Matthieu Olague
Arturo Ocampo
Gerardo Ibarra-Vazquez
Rocio Ochoa
Roberto Pineda
author_sort Gustavo Olague
collection DOAJ
description Despite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progress in this research area follows the traditional path of hand-made designs using neuroscience knowledge or, more recently, deep learning, a particular branch of machine learning. Recently, a different approach based on genetic programming appeared to enhance handcrafted techniques following two different strategies. The first method follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The second approach improves the inner computational structures of basic hand-made models through artificial evolution. This research proposes expanding the artificial dorsal stream using a recent proposal based on symbolic learning to solve salient object detection problems following the second technique. This approach applies the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in an extensive comparison with the state of the art, including classical methods and deep learning approaches to highlight the importance of symbolic learning in visual saliency.
first_indexed 2024-03-09T20:45:14Z
format Article
id doaj.art-f183c7f9182641e1bfa3be5fa8b570f4
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-09T20:45:14Z
publishDate 2022-10-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-f183c7f9182641e1bfa3be5fa8b570f42023-11-23T22:48:46ZengMDPI AGApplied Sciences2076-34172022-10-0112201068610.3390/app122010686Automated Design of Salient Object Detection Algorithms with Brain ProgrammingGustavo Olague0Jose Armando Menendez-Clavijo1Matthieu Olague2Arturo Ocampo3Gerardo Ibarra-Vazquez4Rocio Ochoa5Roberto Pineda6CICESE Research Center, EvoVisión Laboratory, Department of Computer Science, Carretera Tijuana-Ensenada 3918, Zona Playitas, Ensenada C.P. 22860, MexicoCICESE Research Center, EvoVisión Laboratory, Department of Computer Science, Carretera Tijuana-Ensenada 3918, Zona Playitas, Ensenada C.P. 22860, MexicoMechatronics Engineering Faculty, Anáhuac University–Queretaro, Calle Circuito Universidades I, Kilómetro 7, Fracción 2, El Marqués, Queretaro C.P. 76246, MexicoFaculty of Higher Studies Aragón, National Autonomous University of Mexico, Av Hacienda de Rancho Seco S/N, Impulsora Popular Avicola, Nezahualcóyotl C.P. 57130, MexicoFacultad de Ingeniería, Autonomous University of San Luis Potosí, Dr. Manuel Nava 8, Col. Zona Universitaria Poniente, San Luis Potosí C.P. 78290, MexicoFacultad de Ciencias Básicas Ingeniería y Tecnología, Autonomous University of Tlaxcala, Carretera Apizaquito S/N, San Luis Apizaquito, Apizaco C.P. 90401, MexicoCICESE Research Center, EvoVisión Laboratory, Department of Computer Science, Carretera Tijuana-Ensenada 3918, Zona Playitas, Ensenada C.P. 22860, MexicoDespite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progress in this research area follows the traditional path of hand-made designs using neuroscience knowledge or, more recently, deep learning, a particular branch of machine learning. Recently, a different approach based on genetic programming appeared to enhance handcrafted techniques following two different strategies. The first method follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The second approach improves the inner computational structures of basic hand-made models through artificial evolution. This research proposes expanding the artificial dorsal stream using a recent proposal based on symbolic learning to solve salient object detection problems following the second technique. This approach applies the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in an extensive comparison with the state of the art, including classical methods and deep learning approaches to highlight the importance of symbolic learning in visual saliency.https://www.mdpi.com/2076-3417/12/20/10686visual attentiongenetic programmingsalient object detection
spellingShingle Gustavo Olague
Jose Armando Menendez-Clavijo
Matthieu Olague
Arturo Ocampo
Gerardo Ibarra-Vazquez
Rocio Ochoa
Roberto Pineda
Automated Design of Salient Object Detection Algorithms with Brain Programming
Applied Sciences
visual attention
genetic programming
salient object detection
title Automated Design of Salient Object Detection Algorithms with Brain Programming
title_full Automated Design of Salient Object Detection Algorithms with Brain Programming
title_fullStr Automated Design of Salient Object Detection Algorithms with Brain Programming
title_full_unstemmed Automated Design of Salient Object Detection Algorithms with Brain Programming
title_short Automated Design of Salient Object Detection Algorithms with Brain Programming
title_sort automated design of salient object detection algorithms with brain programming
topic visual attention
genetic programming
salient object detection
url https://www.mdpi.com/2076-3417/12/20/10686
work_keys_str_mv AT gustavoolague automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT josearmandomenendezclavijo automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT matthieuolague automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT arturoocampo automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT gerardoibarravazquez automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT rocioochoa automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming
AT robertopineda automateddesignofsalientobjectdetectionalgorithmswithbrainprogramming