Comparison of Two Objects Classification Techniques using Hidden Markov Models and Convolutional Neural Networks
| Autor: | Jesus Savage, Carlos Sarmiento |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Sequence
Contextual image classification Computer Networks and Communications Computer science business.industry Applied Mathematics 05 social sciences Pattern recognition Statistical model 02 engineering and technology Convolutional neural network Computational Mathematics Computational Theory and Mathematics Artificial Intelligence 0502 economics and business 0202 electrical engineering electronic engineering information engineering 050211 marketing 020201 artificial intelligence & image processing Noise (video) Artificial intelligence Quantization (image processing) Hidden Markov model Cluster analysis business Information Systems |
| Zdroj: | Informatics and Automation. 19:1222-1254 |
| ISSN: | 2713-3206 2713-3192 |
| Popis: | This paper presents a comparison between discrete Hidden Markov Models and Convolutional Neural Networks for the image classification task. By fragmenting an image into sections, it is feasible to obtain vectors that represent visual features locally, but if a spatial sequence is established in a fixed way, it is possible to represent an image as a sequence of vectors. Using clustering techniques, we obtain an alphabet from said vectors and then symbol sequences are constructed to obtain a statistical model that represents a class of images. Hidden Markov Models, combined with quantization methods, can treat noise and distortions in observations for computer vision problems such as the classification of images with lighting and perspective changes.We have tested architectures based on three, six and nine hidden states favoring the detection speed and low memory usage. Also, two types of ensemble models were tested. We evaluated the precision of the proposed methods using a public domain data set, obtaining competitive results with respect to fine-tuned Convolutional Neural Networks, but using significantly less computing resources. This is of interest in the development of mobile robots with computers with limited battery life, but requiring the ability to detect and add new objects to their classification systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|