Research And Implementation Of Autonomous Development Of Garment Style Classification Based On Cognitive Characterstics

Garment style is a concept with very strong subjective, whose decision factors is complex, evaluation standard is strong personalized and style features is developing rapidly, all these features make the recognition and classification of garment style more complex. The traditional style quantitative and classification method could not meet the garment style's characteristic of strong personalized and rapid development, but the human perform very well in the garment style recognition. Aim at the characteristic of garment style, we do research and implementation of autonomous development of garment style classification based on cognitive in these paper. The main achievements are as follows:Firstly, we raised a garment style classification method based on multi-objective MILN (Multi-Layer In-place Learning Network) autonomous development network. This method can resolve garment style's several problems such as complex recognition and classification, the insufficient to meet its features by traditional quantitative and classification method. It can adapt the garment style's other features and solve the garment style's personalized independent classification problems.Secondly, Itti visual attention model could not accomplish the visual attention to some subjective defined object such as clothing components. Based on this, we proposed the visual attention model with MILN autonomous development network. The model establishes an independent Top-down visual attention channel with MILN autonomous development network, and take the multi-objective MILN autonomous development network as repository. It perfectly solves the visual attention problems to clothing component and can provide target inputs to the multi-objective MILN autonomous development network. Thirdly, aim at the problem of garment style's traditional analyzing method could not adapt to the rapidly development of it, we get the garment style feature's analyzing method with LCA. Based on the multi-objective MILN autonomous development network, it gets the feature of specific garment style by analyzing the Lobe in the network. The autonomous development characteristic with MILN autonomous development network solves the contradiction between traditional garment style feature's analyzing method and the rapid development of garment style.At last, by integration of the model and algorithm are given, we design and implement the autonomous development system of garment style classification based on cognitive.