Classification of foreign fibers using deep learning and its implementation on embedded system

In recent years, the foreign fibers in cotton lint significantly affect the quality of the final cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This article proposes an embedded system based on field programmable gate array (FPGA) + digital signal processor (DSP) to recognize and remove foreign fibers mixed in cotton. With substantial tests of this system, we collect massive samples of foreign fibers and fake foreign fibers. Based on these samples, a convolution neural network mode is developed to validate the classification of the suspected targets from the detection subsystem, to improve the detection reliability. After training several model architectures, we find a model with the best balance between performance and computation. The high success rate (up to 96% in the validation set) demonstrates the effectiveness of the model. Moreover, the computation time (5 ms on a single image based on an eight-core DSP) indicates the efficiency of the detection, which ensures the real-time application of the system.

[1]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Junying Chen,et al.  Design considerations of real-time adaptive beamformer for medical ultrasound research using FPGA and GPU , 2012, 2012 International Conference on Field-Programmable Technology.

[3]  Bruno J. T. Fernandes,et al.  Pyramidal neural networks with evolved variable receptive fields , 2018, Neural Computing and Applications.

[4]  Antonio J. Plaza,et al.  Hyperspectral Unmixing on Multicore DSPs: Trading Off Performance for Energy , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Xin Qu,et al.  A Fast Feature Extraction Algorithm for Detection of Foreign Fiber in Lint Cotton within a Complex Background: A Fast Feature Extraction Algorithm for Detection of Foreign Fiber in Lint Cotton within a Complex Background , 2010 .

[6]  Daoliang Li,et al.  A new approach for image processing in foreign fiber detection , 2009 .

[7]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[9]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[10]  José de Jesús Rubio,et al.  SOFMLS: Online Self-Organizing Fuzzy Modified Least-Squares Network , 2009, IEEE Transactions on Fuzzy Systems.

[11]  Jingwei Yang,et al.  Saliency-based color image segmentation in foreign fiber detection , 2013, Math. Comput. Model..

[12]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[13]  Hua Li,et al.  Assessing information security risk for an evolving smart city based on fuzzy and grey FMEA , 2018, J. Intell. Fuzzy Syst..

[14]  Da-Wen Sun,et al.  Inspection and grading of agricultural and food products by computer vision systems—a review , 2002 .

[15]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[16]  Eduardo Ros,et al.  A Comparison of FPGA and GPU for Real-Time Phase-Based Optical Flow, Stereo, and Local Image Features , 2012, IEEE Transactions on Computers.

[17]  Terrence L. Fine,et al.  Feedforward Neural Network Methodology , 1999, Information Science and Statistics.

[18]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  Fuad E. Alsaadi,et al.  Partial-Nodes-Based State Estimation for Complex Networks With Unbounded Distributed Delays , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[22]  Dexiang Deng,et al.  Real-Time Fabric Defect Detection Using Accelerated Small-Scale Over-Completed Dictionary of Sparse Coding , 2016 .

[23]  José de Jesús Rubio,et al.  ANFIS system for classification of brain signals , 2019, J. Intell. Fuzzy Syst..

[24]  Vivek Sarkar,et al.  Heterogeneous work-stealing across CPU and DSP cores , 2015, 2015 IEEE High Performance Extreme Computing Conference (HPEC).

[25]  R. Prabhu.  OpenCV on TI ’ s DSP + ARM ® platforms : Mitigating the challenges of porting OpenCV to embedded platforms Introduction , 2011 .

[26]  Xue Liu,et al.  Experimental Evaluation and Selection of Data Consistency Mechanisms for Hard Real-Time Applications on Multicore Platforms , 2014, IEEE Transactions on Industrial Informatics.

[27]  Shuvra S. Bhattacharyya,et al.  An efficient GPU implementation of a multirate resampler for multi-carrier systems , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[28]  Alan D. George,et al.  Optimization and evaluation of image- and signal-processing kernels on the TI C6678 multi-core DSP , 2014, 2014 IEEE High Performance Extreme Computing Conference (HPEC).

[29]  Daoliang Li,et al.  Applications of computer vision techniques to cotton foreign matter inspection , 2014 .

[30]  Xin Qu,et al.  A Fast Feature Extraction Algorithm for Detection of Foreign Fiber in Lint Cotton within a Complex Background , 2010 .

[31]  José Jesús Rubio.  A method with neural networks for the classification of fruits and vegetables , 2017 .

[32]  P. Tantaswadi,et al.  Machine vision for automated visual inspection of cotton quality in textile industries using color isodiscrimination contour , 1999 .

[33]  Daoliang Li,et al.  An Automated Visual Inspection System for Foreign Fiber Detection in Lint , 2009, 2009 WRI Global Congress on Intelligent Systems.