LSTM based texture classification and defect detection in a fabric

Abstract

Texture classification through deep learning is a science of detecting assumptions from various data through different tools of statistics, machine learning, signal processing and algorithm design. The ultimate aim of textile industries is to produce high quality and defect free fabric to the customers. Traditional methodologies involve manual inspection of every fabric produced which in turn seems to be tedious and time consuming. When Long Short Term Memory (LSTM) is applied to the defect detection and texture classification of a fabric the process leads to high efficiency. Industry can maintain the database which consists of pattern as well as the history of defects present in the fabric. The proposed deep learning technique on LSTM infers the details about the fabric through digital images. The defects in fabric are identified using LSTM method. The defects can be identified irrespective of complex patterns. The obtained images are converted to RGB images and compared with threshold levels for pattern recognition. The obtained factors from proposed technique is pattern of the fabric and location of the defects which include scratches, perforations etc. An unsupervised learning algorithm is proposed to classify the defect percentage present in the fabric and classifying the pattern in the fabric. Here multi-scale curvelet image decomposition and sub band decomposition is used to identify pattern and defects in the fabric. The defect detection involves two different phases. The first phase involves in analyzing defect free images. The second phase incorporated LSTM techniques to identify the defects by using logistic regression. The trained images are decomposed as blocks and the algorithm proposed has the capability to achieve defect detection and pattern recognition in a less computational time.