Surface Grading Using Soft Colour-Texture Descriptors

Abstract

Abstract. This paper presents a new approach to the question of surface grading based on soft colour-texture descriptors and well known classifiers. These descriptors come from global image statistics computed in perceptually uniform colour spaces (CIE Lab or CIE Luv). The method has been extracted and validated using a statistical procedure based on experimental design and logistic regression. The method is not a new theoretical contribution, but we have found and demonstrate that a simple set of global statistics softly describing colour and texture properties, together with well-known classifiers, are powerful enough to meet stringent factory requirements for real-time and performance. These requirements are on-line inspection capability and 95% surface grading accuracy. The approach is also compared with two other methods in the surface grading literature; colour histograms [1] and centile-LBP [8]. This paper is an extension and in-depth development of ideas reported in a previous work [11].

A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques

“…Mandriota et al [84] also applied KNN to classify filter responses and wavelet coefficients to inspect rail surfaces. Contrary to [74,75], the authors did not find any performance improvement on their dataset by increasing the value K. Wiltsh et al [144] used a parametric minimum distance based classifier to inspect steel images. Latif-Amet et al [66] also used a Mahalanobis distance based parametric classifier.…”

“…Representing texture using primitives is also effective, for example the texton representation. However, due to the difficulties in explicitly deriving Figure 2: Example ceramic surfaces with three different chromatic tonalities (images from the authors of [75]).…”

“…Penaranda et al [106] computed the first and second histogram moments of each channel of the RGB colour space as chromatic descriptors to classify tiles according to visual perception. Very recently, Lopez et al [74,75] used higher order histogram moments from each channel in L * a * b * colour space to characterise the colour tonality of ceramic tiles. In [11,12], Boukouvalas et al presented spatial and temporal constancy correction of the image illumination on the surfaces of uniform colour and two-colour (fix) patterned tiles.…”

“…The K-Nearest Neighbour (KNN) classifier is a simple nonparametric supervised distance-based learning algorithm where the pattern is assigned to the class shared by the majority of the K nearest neighbours. In [74,75], Lopez et al used KNN to classify ceramic tile surfaces based on chromatic features extracted from individual channels. The authors also investigated various values of K in terms of classification accuracy.…”

Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY

“…[12,13,21,30,31,38,142,148,149,171,[192][193][194][195] Unsupervised/semi-Statistical/Novelty detection [58,65,86,[89][90][91][92]103,115,129,[196][197][198][199][200][201][202] supervised classifiers Gaussian mixture model [80,[203][204][205] Supervised classification methods incorporate the human model-as discussed in Section 3-where the application is searching for features of a predefined class. Detectable features are predefined and the classifier has to be previously trained to recognize them under supervision [40,65,90,103,142,[161][162][163]. As part of the supervised classifiers, the K-Nearest Neighbor (KNN) classifier is a non-parametric learning algorithm where the output object, classified into classes, uses its local neighborhood to formulate a prediction.…”