|تعداد مشاهده مقاله||2,426,073|
|تعداد دریافت فایل اصل مقاله||1,711,181|
|Journal of Electrical and Computer Engineering Innovations (JECEI)|
|دوره 9، شماره 1، فروردین 2021، صفحه 93-102 اصل مقاله (1.19 M)|
|نوع مقاله: Original Research Paper|
|شناسه دیجیتال (DOI): 10.22061/jecei.2020.7548.404|
|A. Mohammadi Anbaran1؛ P. Torkzadeh* 1؛ R. Ebrahimpour2؛ N. Bagheri3|
|1Electrical Engineering Department, Faculty of Engineering, Islamic Azad University, Science and Research Branch, Tehran, Iran.|
|2Artificial 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.|
|3Communication 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.|
|تاریخ دریافت: 04 خرداد 1399، تاریخ بازنگری: 01 مهر 1399، تاریخ پذیرش: 28 آبان 1399|
|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.
|Gabor Filter؛ FPGA؛ Separable Filter؛ Convolution؛ HMAX Model|
 T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, "Robust object recognition with cortex-like mechanisms,” IEEE Trans. on Pattern Analysis & Machine Intelligence, 29(3): 411-426, 2007.
 S. Liu, Y. Liu, X. Zhu, Z. Liu, G. Huo, T. Ding, et al., "Gabor Filtering and Adaptive Optimization Neural Network for Iris Double Recognition,” in proc. Chinese Conf. on Biometric Recognition: 441-449, 2018.
 Y. Liang, L. Lu, Q. Xiao, and S. Yan, "Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs,” IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, 39(4): 857-870, 2020.
 J. Khosravi, M. Shams Esfandabadi, and R. Ebrahimpour, "Image Registration Based on Sum of Square Difference Cost Function," Journal of Electrical and Computer Engineering Innovations, 6(2): 263-271, 2018.
 G. Orchard, J. G. Martin, R. J. Vogelstein, and R. Etienne-Cummings, "Fast neuromimetic object recognition using FPGA outperforms GPU implementations," IEEE trans. on neural networks and learning systems, 24(8): 1239-1252, 2013.
 A. Al Maashri, M. Cotter, N. Chandramoorthy, M. DeBole, C.-L. Yu, V. Narayanan, et al., "Hardware Acceleration for Neuromorphic Vision Algorithms," Journal of Signal Processing Systems, 70(2): 163-175, 2013.
 S. Moini, B. Alizadeh, M. Emad, and R. Ebrahimpour, "A resource-limited hardware accelerator for convolutional neural networks in embedded vision applications," IEEE Trans. on Circuits and Systems II: Express Briefs, 64(10): 1217-1221, 2017.
 F. Abdi, P. Amiri, and M. H. Refan, "Low Computational Complexity and High Computational Speed in Leading DCD ERLS Algorithm," Journal of Electrical and Computer Engineering Innovations, 7(1): 19-26, 2019.
 L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories," Computer vision and Image understanding, 106(1): 59-70, 2007.
 M. DeBole, Y. Xiao, C.-L. Yu, A. Al Maashri, M. Cotter, C. Chakrabarti, et al., "FPGA-accelerator system for computing biologically inspired feature extraction models," in proc. 45th Asilomar Conference on Signals, Systems and Computers (ASILOMAR): 751-755, 2011.
تعداد مشاهده مقاله: 389
تعداد دریافت فایل اصل مقاله: 384