A vegetable category recognition system: a comparison study for caffe and Chainer DNN frameworks

Deep neural network (DNN) has a deep hierarchy that connects multiple internal layers for feature detection and recognition. In our previous work, we proposed a vegetable recognition system which was based on Caffe framework. In this paper, we propose a vegetable category recognition system using DNN frameworks. We present a Vegeshop tool and website for users. Our system can be accessed ubiquitously from anywhere. We evaluate the performance of our vegetable category recognition using 15 kind of vegetables. Also, we evaluate the performance of learning accuracy and loss for vegetable recognition system which is based on Caffe and Chainer frameworks. In addition, we present the performance of recognition rate for different vegetables with different pixel sizes. The evaluation results show that the learning rate is more than 80%. We noticed that the performance of this recognition system is degraded when the color of the object is yellow. In this case, our system does not recognize the outline of the object by light intensity. From these studies, we found that the results of Caffe are higher than Chainer. For both frameworks, when pixel sizes is $$256\times 256$$256×256, the results of accuracy is increased rapidly with the increase in iterations.

[1]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[2]  Keiji Yanai,et al.  Real-time eating action recognition system on a smartphone , 2014, 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[3]  Kida Takuya,et al.  Two Dimensional Pattern Matching for JPEG Images , 2008 .

[4]  Leonard Barolli,et al.  Performance Evaluation of an Accessory Category Recognition System Using Deep Neural Network , 2016, 2016 19th International Conference on Network-Based Information Systems (NBiS).

[5]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[6]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[7]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[8]  R. E. Uhrig,et al.  Introduction to artificial neural networks , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.

[9]  Hiroyuki Ohsaki,et al.  Community Structure and Interaction Locality in Social Networks , 2015, J. Inf. Process..

[10]  P. Mahesha,et al.  Support vector machine-based stuttering dysfluency classification using GMM supervectors , 2015, Int. J. Grid Util. Comput..

[11]  Leonard Barolli,et al.  VegeShop Tool: A Tool for Vegetable Recognition Using DNN , 2016, BWCCA.

[12]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[13]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[14]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[15]  Nobuo Funabiki,et al.  Classification extension based on IoT-big data analytic for smart environment monitoring and analytic in real-time system , 2017, Int. J. Space Based Situated Comput..

[16]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[17]  Hugo Thienpont,et al.  Photonics enhanced sensors for food monitoring: part 2 , 2017, IEEE Instrumentation & Measurement Magazine.

[18]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[19]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Anderson Rocha,et al.  Automatic Classifier Fusion for Produce Recognition , 2012, 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images.

[21]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[22]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[23]  Leonard Barolli,et al.  An Object Tracking System Based on SIFT and SURF Feature Extraction Methods , 2015, 2015 18th International Conference on Network-Based Information Systems.

[24]  Salvatore Vitabile,et al.  Human-to-human interfaces: emerging trends and challenges , 2011, Int. J. Space Based Situated Comput..

[25]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

[26]  Akio Koyama,et al.  A fast search and classification method of isomorphic polygons in LSI design data using geometric invariant feature value , 2016, Int. J. Space Based Situated Comput..

[27]  Yi Li,et al.  Convolutional Neural Networks for Document Image Classification , 2014, 2014 22nd International Conference on Pattern Recognition.

[28]  Leonard Barolli,et al.  A Vegetable Category Recognition System Using Deep Neural Network , 2016, 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS).

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.