Image Based Recognition - Recent Challenges and Solutions Illustrated on Applications

Abstract

In this paper, problems and solutions for the automatic recognition of miscellaneous materials, especially bulk materials are discussed. The fact that many materials, especially natural materials, have a strong phenotypic variability resulting in high intra-class and low inter-class variability of the calculated features poses a complex recognition problem. The recognition of components of a wheat sample or the classification of mineral aggregates serves as an example to demonstrate different aspects in segmentation, feature extraction, classifier design and complexity assessment. We present a technique for the segmentation of highly overlapping and touching objects into single object images, a proposal for feature selection and classifier parameter optimization, as well as a method to visualise the complexity of a highdimensional recognition problem in a three-dimensional space. Every step of the pattern recognition process needs to be optimized carefully with special attention to the risk of overfitting. Modern processors and the application of field-programmable gate arrays as well as the outsourcing of processing steps to the graphic processing unit speed up the calculation and make real-time computation possible also for highly complex recognition problems such as the quality assurance of bulk materials.

Using Haar-like Features and SVM Classifier for Quality Assurance in a Surgical Mask Production Line

“…Their method performs better than SVM classifier, albeit they have less control over the learning process. Garten et al examine image processing possibilities for industrial applications [7]. With the advent of microelectronics such as microcontrollers, embedded General Purpose GPUs (GPGPU) and especially Field Programmable Gate Arrays (FPGA), there is a growing interest in using image processing methods as parts of the industrial production lines.…”