Chunlei Li, Ruimin Yang, Zhoufeng Liu, Guangshuai Gao and Qiuli Liu
Fabric defect detection plays an important role in textile quality control. The purpose of this paper is to propose a fabric defect detection algorithm using learned…
Abstract
Purpose
Fabric defect detection plays an important role in textile quality control. The purpose of this paper is to propose a fabric defect detection algorithm using learned dictionary-based visual saliency.
Design/methodology/approach
First, the test fabric image is splitted into image blocks, and the learned dictionary with normal samples and defective sample is constructed by selecting the image block local binary pattern features with highest or lowest similarity comparing with the average feature vector; second, the first L largest correlation coefficients between each test image block and the dictionary are calculated, and other correlation coefficients are set to zeros; third, the sum of the non-zeros coefficients corresponding to defective samples is used to generate saliency map; finally, an improve valley-emphasis method can efficiently segment the defect region.
Findings
Experimental results demonstrate that the generated saliency map by the proposed method can efficiently outstand defect region comparing with the state-of-the-art, and segment results can precisely localize defect region.
Originality/value
In this paper, a novel fabric defect detection scheme is proposed via learned dictionary-based visual saliency.
Details
Keywords
Qiuli Su, Aidin Namin and Seth Ketron
This paper aims to investigate textual characteristics of customer reviews that motivate companies to respond (sentiment negativity and sentiment deviation) and how aspects of…
Abstract
Purpose
This paper aims to investigate textual characteristics of customer reviews that motivate companies to respond (sentiment negativity and sentiment deviation) and how aspects of these company responses (response intensity, length and tailoring) affect subsequent customer review quality (comprehensiveness and readability) over time.
Design/methodology/approach
Leveraging a large data set from a leading app website (Shopify), the authors combine text mining, natural language processing (NLP) and big data analysis to examine the antecedents and outcomes of online company responses to reviews.
Findings
This study finds that companies are more likely to respond to reviews with more negative sentiment and higher sentiment deviation scores. Furthermore, while longer company responses improve review comprehensiveness over time, they do not have a significant influence on review readability; meanwhile, more tailored company responses improve readability but not comprehensiveness over time. In addition, the intensity (volume) of company responses does not affect subsequent review quality in either comprehensiveness or readability.
Originality/value
This paper expands on the understanding of online company responses within the digital marketplace – specifically, apps – and provides a new and broader perspective on the motivations and effects of online company responses to customer reviews. The study also extends beyond the short-term focus of prior works and adds to literature on long-term effects of online company responses to subsequent reviews. The findings provide valuable insights for companies (especially those with apps) to enhance their online communication strategies and customer engagement.
Details
Keywords
Kristina K. Lindsey-Hall, Eric J. Michel, Sven Kepes, Ji (Miracle) Qi, Laurence G. Weinzimmer, Anthony R. Wheeler and Matthew R. Leon
The purpose of this manuscript is to provide a step-by-step primer on systematic and meta-analytic reviews across the service field, to systematically analyze the quality of…
Abstract
Purpose
The purpose of this manuscript is to provide a step-by-step primer on systematic and meta-analytic reviews across the service field, to systematically analyze the quality of meta-analytic reporting in the service domain, to provide detailed protocols authors may follow when conducting and reporting these analyses and to offer recommendations for future service meta-analyses.
Design/methodology/approach
Eligible frontline service-related meta-analyses published through May 2021 were identified for inclusion (k = 33) through a systematic search of Academic Search Complete, PsycINFO, Business Source Complete, Web of Science, Google Scholar and specific service journals using search terms related to service and meta-analyses.
Findings
An analysis of the existing meta-analyses within the service field, while often providing high-quality results, revealed that the quality of the reporting can be improved in several ways to enhance the replicability of published meta-analyses in the service domain.
Practical implications
This research employs a question-and-answer approach to provide a substantive guide for both properly conducting and properly reporting high-quality meta-analytic research in the service field for scholars at various levels of experience.
Originality/value
This work aggregates best practices from diverse disciplines to create a comprehensive checklist of protocols for conducting and reporting high-quality service meta-analyses while providing additional resources for further exploration.