Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm
Background and Objectives: Programmable logic devices, such as Field Programmable Gate Arrays, are well-suited for implementing biologically-inspired visual processing algorithms and among those algorithms is HMAX model. This model mimics the feedforward path of object recognition in the visual cort...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Shahid Rajaee Teacher Training University
2021-01-01
|
| Series: | Journal of Electrical and Computer Engineering Innovations |
| Subjects: | |
| Online Access: | https://jecei.sru.ac.ir/article_1490_0ae6cdc236e78f78edacd1d286bd19e1.pdf |
| _version_ | 1811306002579980288 |
|---|---|
| author | A. Mohammadi Anbaran P. Torkzadeh R. Ebrahimpour N. Bagheri |
| author_facet | A. Mohammadi Anbaran P. Torkzadeh R. Ebrahimpour N. Bagheri |
| author_sort | A. Mohammadi Anbaran |
| collection | DOAJ |
| description | Background and Objectives: Programmable logic devices, such as Field Programmable Gate Arrays, are well-suited for implementing biologically-inspired visual processing algorithms and among those algorithms is HMAX model. This model mimics the feedforward path of object recognition in the visual cortex. Methods: HMAX includes several layers and its most computation intensive stage could be the S1 layer which applies 64 2D Gabor filters with various scales and orientations on the input image. A Gabor filter is the product of a Gaussian window and a sinusoid function. Using the separability property in the Gabor filter in the 0° and 90° directions and assuming the isotropic filter in the 45° and 135° directions, a 2D Gabor filter converts to two more efficient 1D filters.Results: The current paper presents a novel hardware architecture for the S1 layer of the HMAX model, in which a 1D Gabor filter is utilized twice to create a 2D filter. Using the even or odd symmetry properties in the Gabor filter coefficients reduce the required number of multipliers by about 50%. The normalization value in every input image location is also calculated simultaneously. The implementation of this architecture on the Xilinx Virtex-6 family shows a 2.83ms delay for a 128×128 pixel input image that is a 1.86X-speedup relative to the last best implementation.Conclusion: In this study, a hardware architecture is proposed to realize the S1 layer of the HMAX model. Using the property of separability and symmetry in filter coefficients saves significant resources, especially in DSP48 blocks. |
| first_indexed | 2024-04-13T08:36:36Z |
| format | Article |
| id | doaj.art-4fecbb90f5f9487080784e0e41879fd6 |
| institution | Directory Open Access Journal |
| issn | 2322-3952 2345-3044 |
| language | English |
| last_indexed | 2024-04-13T08:36:36Z |
| publishDate | 2021-01-01 |
| publisher | Shahid Rajaee Teacher Training University |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering Innovations |
| spelling | doaj.art-4fecbb90f5f9487080784e0e41879fd62022-12-22T02:54:03ZengShahid Rajaee Teacher Training UniversityJournal of Electrical and Computer Engineering Innovations2322-39522345-30442021-01-01919310210.22061/jecei.2020.7548.4041490Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing AlgorithmA. Mohammadi Anbaran0P. Torkzadeh1R. Ebrahimpour2N. Bagheri3Electrical Engineering Department, Faculty of Engineering, Islamic Azad University, Science and Research Branch, Tehran, Iran.Electrical Engineering Department, Faculty of Engineering, Islamic Azad University, Science and Research Branch, Tehran, Iran.Artificial Intelligence Department, Faculty of Computer Engineering, Shahid Rajaee Teacher Training University; Tehran, Iran. School of Cognitive Sciences, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran.Communication Engineering Department, Faculty of Electrical Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran. School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran.Background and Objectives: Programmable logic devices, such as Field Programmable Gate Arrays, are well-suited for implementing biologically-inspired visual processing algorithms and among those algorithms is HMAX model. This model mimics the feedforward path of object recognition in the visual cortex. Methods: HMAX includes several layers and its most computation intensive stage could be the S1 layer which applies 64 2D Gabor filters with various scales and orientations on the input image. A Gabor filter is the product of a Gaussian window and a sinusoid function. Using the separability property in the Gabor filter in the 0° and 90° directions and assuming the isotropic filter in the 45° and 135° directions, a 2D Gabor filter converts to two more efficient 1D filters.Results: The current paper presents a novel hardware architecture for the S1 layer of the HMAX model, in which a 1D Gabor filter is utilized twice to create a 2D filter. Using the even or odd symmetry properties in the Gabor filter coefficients reduce the required number of multipliers by about 50%. The normalization value in every input image location is also calculated simultaneously. The implementation of this architecture on the Xilinx Virtex-6 family shows a 2.83ms delay for a 128×128 pixel input image that is a 1.86X-speedup relative to the last best implementation.Conclusion: In this study, a hardware architecture is proposed to realize the S1 layer of the HMAX model. Using the property of separability and symmetry in filter coefficients saves significant resources, especially in DSP48 blocks.https://jecei.sru.ac.ir/article_1490_0ae6cdc236e78f78edacd1d286bd19e1.pdfgabor filterfpgaseparable filterconvolutionhmax model |
| spellingShingle | A. Mohammadi Anbaran P. Torkzadeh R. Ebrahimpour N. Bagheri Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm Journal of Electrical and Computer Engineering Innovations gabor filter fpga separable filter convolution hmax model |
| title | Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm |
| title_full | Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm |
| title_fullStr | Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm |
| title_full_unstemmed | Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm |
| title_short | Fast and Efficient Hardware Implementation of 2D Gabor Filter for a Biologically-Inspired Visual Processing Algorithm |
| title_sort | fast and efficient hardware implementation of 2d gabor filter for a biologically inspired visual processing algorithm |
| topic | gabor filter fpga separable filter convolution hmax model |
| url | https://jecei.sru.ac.ir/article_1490_0ae6cdc236e78f78edacd1d286bd19e1.pdf |
| work_keys_str_mv | AT amohammadianbaran fastandefficienthardwareimplementationof2dgaborfilterforabiologicallyinspiredvisualprocessingalgorithm AT ptorkzadeh fastandefficienthardwareimplementationof2dgaborfilterforabiologicallyinspiredvisualprocessingalgorithm AT rebrahimpour fastandefficienthardwareimplementationof2dgaborfilterforabiologicallyinspiredvisualprocessingalgorithm AT nbagheri fastandefficienthardwareimplementationof2dgaborfilterforabiologicallyinspiredvisualprocessingalgorithm |