Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition

Here we present a study on the use of non-additive entropy to improve the performance of convolutional neural networks for texture description. More precisely, we introduce the use of a local transform that associates each pixel with a measure of local entropy and use such alternative representation as the input to a pretrained convolutional network that performs feature extraction. We compare the performance of our approach in texture recognition over well-established benchmark databases and on a practical task of identifying Brazilian plant species based on the scanned image of the leaf surface. In both cases, our method achieved interesting performance, outperforming several methods from the state-of-the-art in texture analysis. Among the interesting results we have an accuracy of 84.4% in the classification of KTH-TIPS-2b database and 77.7% in FMD. In the identification of plant species we also achieve a promising accuracy of 88.5%. Considering the challenges posed by these tasks and results of other approaches in the literature, our method managed to demonstrate the potential of computing deep learning features over an entropy representation.

Color Classification and Texture Recognition System of Solid Wood Panels

Solid wood panels are widely used in the wood flooring and furniture industries, and paneling is an excellent material for indoor decoration. The classification of colors helps to improve the appearance of wood products assembled from multiple panels due to the differences in surface colors of solid wood panels. Traditional wood surface color classification mainly depends on workers’ visual observations, and manual color classification is prone to visual fatigue and quality instability. In order to reduce labor costs of sorting and to improve production efficiency, in this study, we introduced machine vision technology and an unsupervised learning technique. First-order color moments, second-order color moments, and color histogram peaks were selected to extract feature vectors and to realize data dimension reduction. The feature vector set was divided into different clusters by the K-means algorithm to achieve color classification and, thus, the solid wood panels with similar surface color were classified into one category. Furthermore, during twice clustering based on second-order color moment, texture recognition was realized on the basis of color classification. A sample of beech wood was selected as the research object, not only was color classification completed, but texture recognition was also realized. The experimental results verified the effectiveness of the technical proposal.

Texture Recognition Based on Perception Data from a Bionic Tactile Sensor

Texture recognition is important for robots to discern the characteristics of the object surface and adjust grasping and manipulation strategies accordingly. It is still challenging to develop texture classification approaches that are accurate and do not require high computational costs. In this work, we adopt a bionic tactile sensor to collect vibration data while sliding against materials of interest. Under a fixed contact pressure and speed, a total of 1000 sets of vibration data from ten different materials were collected. With the tactile perception data, four types of texture recognition algorithms are proposed. Three machine learning algorithms, including support vector machine, random forest, and K-nearest neighbor, are established for texture recognition. The test accuracy of those three methods are 95%, 94%, 94%, respectively. In the detection process of machine learning algorithms, the asamoto and polyester are easy to be confused with each other. A convolutional neural network is established to further increase the test accuracy to 98.5%. The three machine learning models and convolutional neural network demonstrate high accuracy and excellent robustness.