使用延伸型限制性波茲曼機於智慧型物件辨識系統

An Intelligent System for Object Recognition Using Extended Restricted Boltzmann Machine

戴志遠(Chih-Yuan Tai)

指導教授 ： 駱榮欽

國立臺北科技大學/電資學院/電腦與通訊研究所/碩士(2012年)

https://doi.org/10.6841/NTUT.2012.00210

摘要

在本文中，我們提出一種使用延伸型限制性波茲曼機實現智慧型物件辨識系統的方法。傳統的類神經網路用於辨識物件是相當出色的，但是局部最小值的問題仍然待解決。因此，提出的方法是一個全域最小值的類神經網路。首先，將物件從攝影機拍攝的影像作分割。為了完整地描述大量的物件，低階的特徵如形狀、紋理和顏色都是必要的。在實際情形，因為低階的特徵含有雜訊，辨識的正確率不太精確。使用已訓練的延伸型限制性波茲曼機，處理的結果是對於物件分類的最佳近似解。最後，在已設計儲存一些高階的規則的知識庫，推論引擎對於結果輸出智慧型解釋。從實驗的結果，證明提出的方法是可行的。

關鍵字

延伸型限制性波茲曼機 ； 全域最小值 ； 描述子

並列摘要

In this paper, we propose an approach that implements an intelligent system for object recognition using Extended Restricted Boltzmann Machine (ERBM). It is excellent to recognize the objects by a typical neural network, but the problem of local minima remains to be solved. Hence, the proposed method is a neural network of global minima. First, objects are segmented from the image which is captured by the camera. In order to describe many kinds of objects completely, low-level features such as shape, texture, and color are essential. Because of some noises of low-level features, the accuracy is not precise in an actual condition. The processed result is the optimum approximate solution for object classification using the trained ERBM. Finally, an inference engine outputs the intelligent explanation for the result in the designed knowledge base which can store some high-level semantic rules. From the experimental results, it is proved that the proposed method is feasible.

並列關鍵字

Extended Restricted Boltzmann Machine ； Global Minima ； Descriptors

參考文獻

[2] Peura, M. and Iivarinen, J., “Efficiency of simple shape descriptors,” In Proceedings of the third international workshop on visual form, pp. 443-451, 1997.

[5] S. B. Kotsiantis, “Supervised Machine Learning A Review of Classification Techniques,” Informatica, volume 31, number 3, pp. 249-268, 2007.

[6] David H. Ackley and Geoffrey E. Hinton, “A Learning Algorithm for Boltzmann Machines,” Cognitive Science, volume 9, issue 1, pp. 147–169, 1985.

[8] Hugo Larochelle and Yoshua Bengio, “Classification using Discriminative Restricted Boltzmann Machines,” Proceedings of the 25th international conference on Machine learning, pp. 536-543, 2008.

[14] Geoffrey E. Hinton, “Training Products of Experts by Minimizing Contrastive Divergence,” Neural Computation, volume 14, no 8, pp. 1771-1800, 2002.