Degumming is the process of removing the sericin or gum from silk yarn. Removing the gum improves the sheen, color, hand, and texture of the silk. Mai 1 silk yarn from Thai hybrid multivoltine Bombyx mori was degummed with commercial grade bromelain and with sodium carbonate. 96.58% of sericin content was removed from the silk yarn in small scale degumming procedure with 2 g/L bromelain and 91.84 % in large scale degumming with 5 g/L bromelain. Scanning electron micrographs of the silk yarn degummed with enzyme showed neither sign of destruction in its morphology nor surface damage. The surface of the yarn degummed with bromelain was smoother than that of the yarn degummed with sodium carbonate. According to the evaluation of its mechanical properties using Kawabata Evaluation System for Fabric, the silk fabric degummed with bromelain showed good tensile strength, better response to bending deformation, higher flexibility, smother feel during bending, and softer and better elastic properties during compression.

SUMMARYThis paper presents an unsupervised learning-based method for selection of feature points and object category classification without previous setting of the number of categories. Our method consists of the following procedures: 1) detection of feature points and description of features using a Scale-Invariant Feature Transform (SIFT), 2) selection of target feature points using One Class-Support Vector Machines (OC-SVMs), 3) generation of visual words of all SIFT descriptors and histograms in each image of selected feature points using Self-Organizing Maps (SOMs), 4) formation of labels using Adaptive Resonance Theory-2 (ART-2), and 5) creation and classification of categories on a category map of Counter Propagation Networks (CPNs) for visualizing spatial relations between categories. Classification results of static images using a Caltech-256 object category dataset and dynamic images using time-series images obtained using a robot according to movements respectively demonstrate that our method can visualize spatial relations of categories while maintaining time-series characteristics. Moreover, we emphasize the effectiveness of our method for category classification of appearance changes of objects.

Ahstract-This paper presents an unsupervised category classification method for time-series images that combines incre mental learning of Adaptive Resonance Theory-2 (ART-2) and self-mapping characteristic of Counter Propagation Networks (CPNs). Our method comprises the following procedures: 1) generating visual words using Self-Organizing Maps (SOM) from 128-dimensional descriptors in each feature point of a Scale-Invariant Feature Transform (SIF T), 2) forming labels using unsupervised learning of ART-2, and 3) creating and classifying categories on a category map of CPNs for visualizing spatial relations between categories. We use a vision system on a mobile robot for taking time-series images. Experimental results show that our method can classify objects into categories according to their change of appearance during the movement of a robot.

No abstract