Quantifying Appearance Retention in Carpets Using Geometrical Local Binary Patterns

Quiñones, Rolando; Orjuela, S. A.; Ortiz-Jaramillo, B.; Langenhove, Lieva Van; Philips, Wilfried

doi:10.1007/978-3-642-23687-7_30

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…25 The technique was previously tested for evaluating global deviations of texture due to degradation in carpets. 26 This technique assigns the LBP-codes by evaluating 'oriented neighbourhoods' (see Section 2) from the pixel instead of the common circular neighbourhood around the pixel. We compare the performance of LBP and GLBP techniques in terms of speed and accuracy when implemented in CPU and GPU environments.…”

Section: Introductionmentioning

confidence: 99%

Fast texture evaluation of textiles using the GLBP technique in GPU architecture

et al. 2012

View full text Add to dashboard Cite

Commonly, visual inspection tasks in the textile industry are performed by human experts. The major drawback of this type of inspection is the human subjectivity, which affects accuracy and repeatability. Objectivity, accuracy and repeatability can be achieved by analysing visual characteristics of the products using computer vision. Particularly, automatic real time inspection systems based on texture analysis can be implemented using Local Binary Pattern (LBP) techniques. A recent variation of the LBP techniques, named Geometric Local Binary Pattern (GLBP) technique, showed an increase in the performance for detecting small changes of local texture. In this paper a real time implementation of the algorithm is presented by using a Graphic Processing Unit (GPU). The LBP and GLBP techniques are compared in terms of speed and accuracy while implemented on a Central Processing Unit (CPU) and GPU environments. Algorithms are tested for detecting defects in fabrics as well as for evaluating global deviations of texture, which are due to the degradation of the surface in carpets. Results show that higher discriminant power between similar textures is obtained when using the GLBP technique

show abstract

Section: Introductionmentioning

confidence: 99%

Fast texture evaluation of textiles using the GLBP technique in GPU architecture

et al. 2012

View full text Add to dashboard Cite

show abstract

“…[6][7][8][9][10] Most of them are focused in texture analysis. 9,11,12 Also, approaches related to assessment by using changes in intensity color have been developed. 13 All these researches have shown promising results, mainly to assess carpets type cut and loop pile.…”

mentioning

confidence: 99%

“…Approaches based on texture analysis for carpet wear assessment have been developed by mean of our scanner. 10,12 Shaggy carpets with thin yarns have been the strong challenge for the assessment, principally for the the aforementioned problems. Thus, additional features must be extracted to assess properly the AR grades in shaggy carpets.…”

mentioning

confidence: 99%

Measuring hairiness in carpets by using surface metrology

et al. 2011

Self Cite

View full text Add to dashboard Cite

Recently, an automatic system for grading appearance retention in carpets using our own scanner and image analysis techniques was proposed. A system for carpets with low pile construction and without color patterns has been developed. Appearance changes in carpets with high pile construction were still not well detected. We present an approach based on surface metrology that extract information given by the hairs on the carpet surface. These features are complementary to the texture features previously explored. By combining both features, we expand the use of the automatic grading system including some carpets types with high pile construction.

show abstract