An intelligent detection and assessment method based on textile fabric image feature

2019 ◽  
Vol 31 (3) ◽  
pp. 390-402 ◽  
Author(s):  
Xueqing Zhao ◽  
Xin Shi ◽  
Kaixuan Liu ◽  
Yongmei Deng

PurposeThe quality of produced textile fibers plays a very important role in the textile industry, and detection and assessment schemes are the key problems. Therefore, the purpose of this paper is to propose a relatively simple and effective technique to detect and assess the quality of produced textile fibers.Design/methodology/approachIn order to achieve automatic visual inspection of fabric defects, first, images of the textile fabric are pre-processed by using Block-Matching and 3-D (BM3D) filtering. And then, features of textile fibers image are respectively extracted, including color, texture and frequency spectrum features. The color features are extracted by using hue–saturation–intensity model, which is more consistent with the human vision perception model; texture features are extracted by using scale-invariant feature transform scheme, which is a quite good method to detect and describe the local image features, and the obtained features are robust to local geometric distortion; frequency spectrum features of textiles are less sensitive to noise and intensity variations than spatial features. Finally, for evaluating the quality of the fabric in real time, two quantitatively metric parameters, peak signal-to-noise ratio and structural similarity, are used to objectively assess the quality of textile fabric image.FindingsCompared to the quality between production and pre-processing of textile fiber images, the BM3D filtering method is a very efficient technology to improve the quality of textile fiber images. Compared to the different features of textile fibers, like color, texture and frequency spectrum, the proposed detection and assessment method based on textile fabric image feature can easily detect and assess the quality of textiles. Moreover, the objective metrics can further improve the intelligence and performance of detection and assessment schemes, and it is very simple to detect and assess the quality of textiles in the textile industry.Originality/valueAn intelligent detection and assessment method based on textile fabric image feature is proposed, which can efficiently detect and assess the quality of textiles, thereby improving the efficiency of textile production lines.

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xueqing Zhao ◽  
Min Zhang ◽  
Junjun Zhang

PurposeClassifying the types of fabric defects in the textile industry requires a way to effectively detect. The traditional textile fabric defects detection method is human eyes, which performs very low efficiency and high cost. Therefore, how to improve the classification accuracy of textile fabric defects by using current artificial intelligence and to better meet the needs in the textile industry, the purpose of this article is to develop a method to improve the accuracy of textile fabric defects classification.Design/methodology/approachTo improve the accuracy of textile fabric defects classification, an ensemble learning-based convolutional neural network (CNN) method in terms of textile fabric defects classification (short for ECTFDC) on an enhanced TILDA database is used. ECTFDC first adopts ensemble learning-based model to classify five types of fabric defects from TILDA. Subsequently, ECTFDC extracts features of fabric defects via an ensemble multiple convolutional neural network model and obtains parameters by using transfer learning method.FindingsThe authors applied ECTFDC on an enhanced TILDA database to improve the robustness and generalization ability of the proposed networks. Experimental results show that ECTFDC outperforms the other networks, the precision and recall rates are 97.8%, 97.68%, respectively.Originality/valueThe ensemble convolutional neural network textile fabric defect classification method in this paper can quickly and effectively classify textile fabric defect categories; it can reduce the production cost of textiles and it can alleviate the visual fatigue of inspectors working for a long time.


Author(s):  
Jared Michael Noynaert ◽  
Regan Potangaroa

Purpose This paper aims to examine accurate cross-sector assessment of true relative need in affected populations and the net human impact of disaster response programmes. Design/methodology/approach A psychometric assessment method using the DASS-42 is presented, and its practicality and value are shown through field studies in Afghanistan and Vanuatu. Findings Psychometric quality of life assessments are robust, rapidly deployable, culturally and sector-agnostic, and imminently useful for targeting disaster aid and measuring programme effectiveness. Research limitations/implications This research provides a baseline for further investigation into identifying which aid interventions are necessary without using technical assessments. Practical implications The demonstrated method is more effective in many situations than traditional technical assessments or assumption of which demographic factors place groups at risk. Originality/value The identified approach builds on previous work by combining psychometric indications of disaster effect with specific areas of need self-identified by the assessed communities. Its effectiveness for enabling humanitarian action at both large and small scales is also proven.


2012 ◽  
Vol 476-478 ◽  
pp. 2014-2019
Author(s):  
Xiao Jiang ◽  
Long Di Cheng ◽  
Jian Yong Yu ◽  
Qin Wang ◽  
Elena Stojanovska ◽  
...  

The akund fiber has great potential to be used in the textile industry benefiting from its excellent properties. The adoption of akund fiber from calotropis gigantea could substitute or supplement cotton as raw materials for textile fabric and might reduce the possible damage to the environment. Therefore, The study in this paper on the relationship between carding procedure and the quality of akund fiber sliver aimed at optimizing the process of this new kind fiber on a flat top card has significant meaning. The results in this paper show that high quality slivers can be produced by using new wires, low speed of card elements or proper akund fiber content in blended yarn. However, decreasing the number of moving flats in the main carding zone too much would deteriorate the sliver quality.


2020 ◽  
Vol 38 (5/6) ◽  
pp. 861-880
Author(s):  
Chien-Min Kuo ◽  
Kuan-Yu Chen ◽  
Yi-Ching Lin

Purpose Teachers, students, librarians, scholars and domain experts often spend a lot of time and effort to select good and suitable textbooks. This study aims to propose and construct a computer-aided bibliometric system to rate textbooks. Through the software system designed here, the quality of every textbook can be easily and quickly known. This system will benefit both scholars and librarians. Design/methodology/approach Four methods were used to evaluate textbooks in this study, including: questionnaire recommendation analysis, dissertation citation analysis, library circulation analysis and bibliography analysis. The system architecture includes three subsystems: the textbook indexing and searching subsystem, the statistics added-value analysis subsystem and the citation report inquiry subsystem. An example demonstrates the usability and validity of the proposed method and system. The example uses surveying textbooks. The following percentages were used in the correlation calculation: textbook citation percentage (TCP), textbook library circulation percentage (TLP) and textbook recommend percentage (TRP). Findings There are three textbook assessment methods applied in this study, including: dissertation citation, library circulation and questionnaire recommendation. Dissertation citations for textbooks have a high correlation value with library circulation. The frequency correlation calculation was 0.7, while the TCP, TLP and TRP correlation calculation was 0.84. Therefore, the dissertation citation method can be accepted to evaluate textbooks effectively. Originality/value To the best of the authors’ knowledge, this is the first work related to evaluating surveying textbooks using a computer-aided bibliometrics system that can deal with large amounts of data and generate results quickly. This can be applied to other fields as well.


2019 ◽  
Vol 36 (4) ◽  
pp. 322-341 ◽  
Author(s):  
Jose Manuel Azevedo ◽  
Ema P. Oliveira ◽  
Patrícia Damas Beites

Purpose The purpose of this paper is to find appropriate forms of analysis of multiple-choice questions (MCQ) to obtain an assessment method, as fair as possible, for the students. The authors intend to ascertain if it is possible to control the quality of the MCQ contained in a bank of questions, implemented in Moodle, presenting some evidence with Item Response Theory (IRT) and Classical Test Theory (CTT). The used techniques can be considered a type of Descriptive Learning Analytics since they allow the measurement, collection, analysis and reporting of data generated from students’ assessment. Design/methodology/approach A representative data set of students’ grades from tests, randomly generated with a bank of questions implemented in Moodle, was used for analysis. The data were extracted from a Moodle database using MySQL with an ODBC connector, and collected in MS ExcelTM worksheets, and appropriate macros programmed with VBA were used. The analysis with the CTT was done through appropriate MS ExcelTM formulas, and the analysis with the IRT was approached with an MS ExcelTM add-in. Findings The Difficulty and Discrimination Indexes were calculated for all the questions having enough answers. It was found that the majority of the questions presented values for these indexes, which leads to a conclusion that they have quality. The analysis also showed that the bank of questions presents some internal consistency and, consequently, some reliability. Groups of questions with similar features were obtained, which is very important for the teacher to develop tests as fair as possible. Originality/value The main contribution and originality that can be found in this research is the definition of groups of questions with similar features, regarding their difficulty and discrimination properties. These groups allow the identification of difficulty levels in the questions on the bank of questions, thus allowing teachers to build tests, randomly generated with Moodle, that include questions with several difficulty levels in the tests, as it should be done. As far as the authors’ knowledge, there are no similar results in the literature.


Sensor Review ◽  
2014 ◽  
Vol 34 (4) ◽  
pp. 404-409
Author(s):  
Abbas Hajipour ◽  
Ali Shams Nateri ◽  
Alireza Sadr Momtaz

Purpose – This study aimed to use a scanner as a low-cost method for measuring the opacity of textile fabric. Textile fabrics must have specific ranges of opacity according to their uses for shirting, curtaining, etc. In this way, opacity is an important property in the textile industry. Conventionally, textile opacity is estimated using a spectrophotometer, which is an expensive method. Design/methodology/approach – In this study a scanner was used as a low-cost method for measuring the opacity of textile fabric. The opacity was estimated by using red, green and blue (RGB) parameters of images of fabric against white and black background. Findings – The accuracy of opacity estimation was improved by converting RGB into several color spaces. The best opacity estimation was obtained by using the XYZ color space. In addition, using a regression method, the best estimation was obtained by using a fourth-order polynomial regression with the LSLM color space. Originality/value – The opacity of fabric has been measured by spectrophotometer, but in this study, the opacity of fabric was measured by scanner as a low cost device and also with novel and simple method. This method achieved acceptable accuracy for opacity estimation. The obtained result is comparable with spectrophotometer results.


2020 ◽  
Vol 64 (1) ◽  
pp. 10505-1-10505-16
Author(s):  
Yin Zhang ◽  
Xuehan Bai ◽  
Junhua Yan ◽  
Yongqi Xiao ◽  
C. R. Chatwin ◽  
...  

Abstract A new blind image quality assessment method called No-Reference Image Quality Assessment Based on Multi-Order Gradients Statistics is proposed, which is aimed at solving the problem that the existing no-reference image quality assessment methods cannot determine the type of image distortion and that the quality evaluation has poor robustness for different types of distortion. In this article, an 18-dimensional image feature vector is constructed from gradient magnitude features, relative gradient orientation features, and relative gradient magnitude features over two scales and three orders on the basis of the relationship between multi-order gradient statistics and the type and degree of image distortion. The feature matrix and distortion types of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion type; the feature matrix and subjective scores of known distorted images are used to train an AdaBoost_BP neural network to determine the image distortion degree. A series of comparative experiments were carried out using Laboratory of Image and Video Engineering (LIVE), LIVE Multiply Distorted Image Quality, Tampere Image, and Optics Remote Sensing Image databases. Experimental results show that the proposed method has high distortion type judgment accuracy and that the quality score shows good subjective consistency and robustness for all types of distortion. The performance of the proposed method is not constricted to a particular database, and the proposed method has high operational efficiency.


2019 ◽  
Vol 26 (4) ◽  
pp. 340-351
Author(s):  
Alberto Carlo Cajavilca ◽  
Marta Tostes

Purpose The purpose of this paper is to examine the role and contribution of San Martin and Chazuta subnational governments in promoting development and internationalization of the cocoa and chocolate value chain from the stakeholders’ perceptions. This work was based on a qualitative approach in which information triangulation method, information processing with evaluation rubric and WebQDA software were used. The results showed that stakeholders of both value chains perceive that the subnational government’s actions taken to develop and internationalize these value chains are poorly valued and insufficient. Likewise, six internationalization barriers were identified in which two are perceived as the main limitations: low productivity levels and access to innovations and technology. These results contribute to enrich the decision-making process of political authorities and public officials from the San Martin subnational governments. Moreover, they provide information, according to the Peruvian national requirements, on the perceptions needed to rethink and improve the governmental services available, especially productive activities in the rainforest area (Presidencia del Consejo de Ministros, 2015; Wiener Fresco, 2010). This can improve or create new extension services to increase the quality of the Chazuta’s cocoa and chocolate products and to facilitate their entry into more demanding and profitable markets (Shapira, y otros, 2015). Design/methodology/approach This paper has been developed by using a qualitative approach with an exploratory and descriptive scope. The objective was to examine a study case of how subnational governments contribute in the promotion of development and internationalization of agro-industrial value chains as alternatives to illicit crops (Hernandez, Fernandez, & Baptista, 2010). The Chazuta case was selected because it is representative of the region in terms of coca eradication and is located between two regions of high biodiversity – Cordillera Escalera Regional Conservation Area and Cordillera Azul National Park. Findings One of the issues hindering the ability of the Chazuta cocoa and chocolate producers is based on their perception that the subnational governments’ efforts are focused on meeting already-established goals and little emphasis is placed on solving productive problems. On the other hand, at an articulation level, the most relevant efforts have been connecting the cocoa and chocolate customers to Chazuta producers through events. In spite of this, such events are not considered a permanent activity and the producers do not perceive that these mechanisms enable them to maintain these long-term trade relationships. This can be explained by the fact that Chazuta cocoa and chocolate organizations recognize that they still have incipient productive capacities to meet the foreign market’s demand. Furthermore, associations, cooperatives and SMEs are not able to maintain constant levels of production quality, except the family-based business. Knowledge and techniques provided by subnational governments and private organizations are not fully used or implemented by the associations’ members. This low level of knowledge application can be explained by cultural factors and also because the producers receive multiple and sometimes contradictory information from various providers of technology extension services. This leads to inadequate use or non-implementation of productivity improvements, thus generating a virtuous circle in which production and quality of the goods remain at low levels, which hinders their entry into demanding and profitable markets. Research limitations/implications This paper has been developed with a qualitative approach considering an exploratory and descriptive scope. Chazuta case was selected because it is representative of the region in terms of eradication achievements and it is located between two regions of high biodiversity. A rubric is an evaluation method of individuals or organizations performance, taking into consideration the evaluator’s pre-established criteria to determine if the objectives and goals are being met. Based on these criteria, evidence and performance information is collected. Following, performance is graded based on the researcher’s predetermined criteria and finally a merit-based judgment is made on the performance. Practical implications The results contribute to enrich decision making of political authorities and public officials from San Martin subnational governments. They provide information, according to Peruvian national requirements, on the perceptions needed to rethink and improve provided government services, especially in rainforest area productive activities. This adds up to improvement or creation of new extension services to increase the quality of Chazuta’s cocoa and chocolate products, and to facilitate their entry into more demanding and profitable markets. Social implications The situation of San Martín region and Chazuta district is contextualized and emphasis is given to socioeconomic conditions and the value of cocoa as an alternative crop to coca. From 1980 to early 2000, Peru lived a period of generalized violence due to narcoterrorism, which had large-scale outreach in southern highland and rainforest areas. To deal with this situation, subnational governments in collaboration with international cooperation decided to consolidate agro-industrial value chains in order to generate legal income for rural populations. For this purpose, alternative crop policies were implemented and San Martin region achieved the best results. Originality/value This fieldwork was carried out as part of the undergraduate thesis but after fieldwork, with the use of online software tool WebQDA, codes were created to systematize and quantify the collected information in the content manager. The codes were created taking into account assessment and evaluation variables. Each value represented a code referred to a performance level as perceived by Chazuta cocoa and chocolate value chains stakeholders.


2019 ◽  
Vol 19 (6) ◽  
pp. 1344-1361
Author(s):  
Isaiah Oino

Purpose The purpose of this paper is to examine the impact of transparency and disclosure on the financial performance of financial institutions. The emphasis is on assessing transparency and disclosure; auditing and compliance; risk management as indicators of corporate governance; and understanding how these parameters affect bank profitability, liquidity and the quality of loan portfolios. Design/methodology/approach A sample of 20 financial institutions was selected, with ten respondents from each, yielding a total sample size of 200. Principal component analysis (PCA), with inbuilt ability to check for composite reliability, was used to obtain composite indices for the corporate governance indicators as well as the indicators of financial performance, based on a set of questions framed for each institution. Findings The analysis demonstrates that greater disclosure and transparency, improved auditing and compliance and better risk management positively affect the financial performance of financial institutions. In terms of significance, the results show that as the level of disclosure and transparency in managerial affairs increases, the performance of financial institutions – as measured in terms of the quality of loan portfolios, liquidity and profitability – increases by 0.3046, with the effect being statistically significant at the 1 per cent level. Furthermore, as the level of auditing and the degree of compliance with banking regulations increases, the financial performance of banks improves by 0.3309. Research limitations/implications This paper did not consider time series because corporate governance does not change periodically. Practical implications This paper demonstrates the importance of disclosure and transparency in managerial affairs because the performance of financial institutions, as measured in terms of loan portfolios, liquidity and profitability, increases by 0.4 when transparency and disclosure improve, with this effect being statistically significant at the 1 per cent level. Originality/value The use of primary data in assessing the impact of corporate governance on financial performance, instead of secondary data, is the primary novelty of this study. Moreover, PCA is used to assess the weight of the various parameters.


2019 ◽  
Vol 14 (4) ◽  
pp. 251-263
Author(s):  
Daniel J. Carabellese ◽  
Michael J. Proeve ◽  
Rachel M. Roberts

Purpose The purpose of this paper is to explore the relationship of two distinct variants of dispositional shame (internal and external shame) with collaborative, purpose-driven aspects of the patient–provider relationship (working alliance) and patient satisfaction. The aim of this research was to conduct a preliminary investigation into the relevance of dispositional shame in a general healthcare population. Design/methodology/approach In total, 127 community members (mean age 25.9 years) who reported that they had regularly seen a GP over the past year were recruited at an Australian university. Participants were asked to reflect on their relationship with their GP, and completed instruments assessing various domains of shame, as well as working alliance and patient satisfaction. Findings Non-parametric correlations were examined to determine the direction and strength of relationships, as well as conducting mediation analyses where applicable. Small, negative correlations were evident between external shame and working alliance. Both external and internal shame measures were also negatively correlated with patient satisfaction. Finally, the relationship of external shame to patient satisfaction was partially mediated by working alliance. Practical implications Both the reported quality of patient–provider working alliance, and level of patient satisfaction are related to levels of dispositional shame in patients, and working alliance may act as a mediator for this relationship. Originality/value The findings from this preliminary study suggest that internal and external shame are important factors to consider in the provision of medical care to maximise the quality of patient experience and working alliance.


Sign in / Sign up

Export Citation Format

Share Document