Global and local features for accurate impression estimation of cloth fabric images

Huang, Xinyin; Chen, Dingye; Han, Xian-Hua; Chen, Yen‐Wei

doi:10.1109/sii.2013.6776758

Cited by 5 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al [24] create 3D garment models from a single image. Huang et al [5] use both global and local features to improve the estimation accuracy of cloth fabric images. Ramisa et al [14] use depth and appearance features for informing robot grasping of highly wrinkled clothes.…”

Section: Related Workmentioning

confidence: 99%

An Approach for Clothing Recommendation Based on Multiple Image Attributes

Sha

Wang

Zhou

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Currently, many online shopping websites recommend commodities to users according to their purchase history and the behaviors of others who have similar history with the target users. Most recommendations are conducted by commodity tags based similarity search. However, clothing purchase has some specialized characteristics, i.e. users usually don't like to go with the crowd blindly and will not buy the same clothing twice. Moreover, the text tags cannot express clothing features accurately enough. In this paper we propose a novel approach that extracts multi-features from images to analyze its content in different attributes for clothing recommendation. Specifically, a color matrix model is proposed to distinguish split joint clothing. ULBP feature is extracted to represent fabric pattern attribute. PHOG, Fourier, and GIST features are extracted to describe collar and sleeve attributes. Then, some classifiers are trained to classify clothing fabric patterns and split joint types. Experiments based on every attribute and their combinations have been done respectively, and have achieved satisfied results.

show abstract

Section: Related Workmentioning

confidence: 99%

An Approach for Clothing Recommendation Based on Multiple Image Attributes

Sha

Wang

Zhou

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Similarity perception, as a very important aspect of visual perception, plays an essential role in scene and object recognition [22,23]. It is regarded as one of the variables that affects global and local processing [24].…”

Section: Introductionmentioning

confidence: 99%

Influences of Global and Local Features on Eye-Movement Patterns in Visual-Similarity Perception of Synthesized Texture Images

Guo

Asano

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Global and local features are essential for visual-similarity texture perception. Therefore, understanding how people allocate their visual attention when viewing textures with global or local similarity is important. In this work, we investigate the influences of global and local features of a texture on eye-movement patterns and analyze the relationship between eye-movement patterns and visual-similarity selection. First, we synthesized textures by separately controlling global and local textural features through the primitive, grain, and point configuration (PGPC) texture model, a mathematical morphology-based texture model. Second, we conducted an experiment to acquire eye-movement data where participants identified the texture that was highly similar to the standard texture. Experiment data were obtained through an eye-tracker from 60 participants. The collected eye-tracking data were analyzed in terms of three metrics, including total fixation duration in each region of interest (ROI), fixation-point variance in each ROI, and fixation-transfer counts between different ROIs. Analysis results indicated the following. (1) The global and local features of a texture influenced eye-movement patterns. In particular, the texture image that was globally similar to the standard texture contained dispersed fixation points. By contrast, the texture image that was locally similar to the standard texture contained concentrated fixation points. The domination of global and local features influenced the viewers’ similarity choice. (2) The final visual-similarity selection was related to the fixation-transfer count between different ROIs, but not to the fixation time in each ROI. This research also extends the applicability of the mathematical morphology-based texture model to human visual perception.

show abstract

“…The Semantic Differential Scale for hard-soft bipolar adjectives 1997; Nagamachi, 1994), doors (Matsubara & Nagamachi, 1997), microelectronics (Chuang & Ma, 2001), mobile phones (Chuang, Chang, & Hsu, 2001), office chairs (Hsiao & Huang, 2002;Jindo, Hirasago, & Nagamachi, 1995), printers (Chang & Van, 2003), glasses (Petiot & Yannou, 2004), footwear (Alcántara, Artacho, González, & Garcia, 2005), rock switch (Schütte & Eklund, 2005), cloth fabric (Huang, Chen, Han, & Chen, 2013), ketchup sauce bottle (Mamaghani, Rahimian, & Mortezaei, 2014), kitchen products (Bevan, Liu, Barnes, Hassenzahl, & Wei, 2016) Sáa, Gil, González-Rodríguez, López, & Lubiano, 2015;Stevens & Galanter, 1957). This fact reduces the measurement level of the data from interval to the ordinal level and so retrieved data from the scale fail to satisfy assumptions required by parametric statistical analysis (Schutz & Cardello, 2001).…”

Section: Introductionmentioning

confidence: 99%

“…Many applications are found in the literature that apply SDS for evaluating products, for example, the design of street furniture (Maurer, Overbeeke, & Smets, 1992), car interior (Jindo & Hirasago, 1997; Nagamachi, 1994), doors (Matsubara & Nagamachi, 1997), microelectronics (Chuang & Ma, 2001), mobile phones (Chuang, Chang, & Hsu, 2001), office chairs (Hsiao & Huang, 2002; Jindo, Hirasago, & Nagamachi, 1995), printers (Chang & Van, 2003), glasses (Petiot & Yannou, 2004), footwear (Alcántara, Artacho, González, & Garcia, 2005), rock switch (Schütte & Eklund, 2005), cloth fabric (Huang, Chen, Han, & Chen, 2013), ketchup sauce bottle (Mamaghani, Rahimian, & Mortezaei, 2014), kitchen products (Bevan, Liu, Barnes, Hassenzahl, & Wei, 2016), anthropomorphic package shapes (De Bondt, Van Kerckhove, & Geuens, 2018), and others.…”

Section: Introductionmentioning

confidence: 99%

Developing a Labeled Affective Magnitude scale and Fuzzy Linguistic scale for tactile feeling

Akay

Duran

et al. 2020

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

Affective design is the inclusion or representation of human emotions and subjective impressions in product design processes. In affective design, a number of different scales are commonly used to reveal and measure subjective emotions related to the design features of products. Osgood's Semantic Differential Scale (SDS) is one of the scales that has often been used for this purpose. However, there are some drawbacks in the SDS due to the ordinal nature of the scale that leads to losses or distortions of a significant amount of information and this makes it difficult to justify parametric statistical analysis. In this study, two scales, namely a Labeled Affective Magnitude (LAM) scale and a Fuzzy Linguistic scale, are developed. The LAM scale is an alternative scale based on magnitude estimation and has ratio properties. The Fuzzy Linguistic scale is an interval scale for which responses are

show abstract

Global and local features for accurate impression estimation of cloth fabric images

Cited by 5 publications

References 3 publications

An Approach for Clothing Recommendation Based on Multiple Image Attributes

An Approach for Clothing Recommendation Based on Multiple Image Attributes

Influences of Global and Local Features on Eye-Movement Patterns in Visual-Similarity Perception of Synthesized Texture Images

Developing a Labeled Affective Magnitude scale and Fuzzy Linguistic scale for tactile feeling

Contact Info

Product

Resources

About