Randomized neural network based signature for color texture classification prism dimension.
SÁ JUNIOR, Jarbas Joaci de Mesquita; BACKES, André Ricardo; BRUNO, Odemir Martinez.
SÁ JUNIOR, Jarbas Joaci de Mesquita; BACKES, André Ricardo; BRUNO, Odemir Martinez.
 Abstract: Color texture analysis is an important subject in computer vision research. This paper presents an innovative and powerful color texture analysis method based on a randomized neural network. This approach uses the weights of the neural network as attributes for a color feature vector. Experiments were performed in three well-established benchmarks (Vistex, USPtex and Outex) and two rotated versions of these datasets (Vistex and Outex). The results were promising, surpassing the accuracies of most of the compared methods. This achievement allows us to affirm that the proposed approach is a valuable tool to be included in color texture analysis field. | |
| Multidimensional Systems and Signal Processing |
| v. 30, n. 3, p. 1171-1186 - Ano: 2019 |
| Fator de Impacto: 2,338 |
| http://dx.doi.org/10.1007/s11045-018-0600-6 |  @article={002952008,author = {SÁ JUNIOR, Jarbas Joaci de Mesquita; BACKES, André Ricardo; BRUNO, Odemir Martinez.},title={Randomized neural network based signature for color texture classification prism dimension},journal={Multidimensional Systems and Signal Processing},note={v. 30, n. 3, p. 1171-1186},year={2019}} |