COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT
Recently, problems of digital image sharpness determination are becoming more relevant and significant. The number of digital images used in many fields of science and technology is growing. Images obtained in various ways may have unsatisfactory quality; therefore, an important step in image proces...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Educational institution «Belarusian State University of Informatics and Radioelectronics»
2019-12-01
|
| Series: | Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki |
| Subjects: | |
| Online Access: | https://doklady.bsuir.by/jour/article/view/2178 |
| _version_ | 1797881031378862080 |
|---|---|
| author | Y. I. Golub F. V. Starovoitov V. V. Starovoitov |
| author_facet | Y. I. Golub F. V. Starovoitov V. V. Starovoitov |
| author_sort | Y. I. Golub |
| collection | DOAJ |
| description | Recently, problems of digital image sharpness determination are becoming more relevant and significant. The number of digital images used in many fields of science and technology is growing. Images obtained in various ways may have unsatisfactory quality; therefore, an important step in image processing and analysis algorithms is a quality control stage of the received data. Poor quality images can be automatically deleted. In this article we study the problem of the automatic sharpness evaluation of digital images. As a result of the scientific literature analysis, 28 functions were selected that are used to analyze the clarity of digital images by calculation local estimates. All the functions first calculate local estimates in the neighborhood of every pixel, and then use the arithmetic mean as a generalized quality index. Testing have demonstrated that many estimates of local sharpness of the image often have abnormal distribution of the data. Therefore, some modified versions of the studied functions were additionally evaluated, instead of the average of local estimates, we studied the Weibull distribution parameters (FORM, SCALE, MEAN weib, MEDIAN weib). We evaluated three variants of the correlation of quantitative sharpness assessments with the subjective assessments of human experts. Since distribution of local features is abnormal, Spearman and Kendall rank correlation coefficients were used. Correlation above 0.7 means good agreement between quantitative and visual estimates. The experiments were carried out on digital images of various quality and clarity: artificially blurred images and blurred during shooting. Summing up results of the experiments, we propose to use seven functions for automatic analysis of the digital image sharpness, which are fast calculated and better correlated with the subjective sharpness evaluation. |
| first_indexed | 2024-04-10T03:12:35Z |
| format | Article |
| id | doaj.art-acd6a39a88fb4433b4b683d3c4ec7e36 |
| institution | Directory Open Access Journal |
| issn | 1729-7648 |
| language | Russian |
| last_indexed | 2024-04-10T03:12:35Z |
| publishDate | 2019-12-01 |
| publisher | Educational institution «Belarusian State University of Informatics and Radioelectronics» |
| record_format | Article |
| series | Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki |
| spelling | doaj.art-acd6a39a88fb4433b4b683d3c4ec7e362023-03-13T07:33:20ZrusEducational institution «Belarusian State University of Informatics and Radioelectronics»Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki1729-76482019-12-0107 (125)11312010.35596/1729-7648-2019-125-7-113-1201368COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENTY. I. Golub0F. V. Starovoitov1V. V. Starovoitov2State Scientific Institution “The United Institute of Informatics Problems of the National Academy of Sciences of Belarus”The Belarusian National Technical UniversityState Scientific Institution “The United Institute of Informatics Problems of the National Academy of Sciences of Belarus”Recently, problems of digital image sharpness determination are becoming more relevant and significant. The number of digital images used in many fields of science and technology is growing. Images obtained in various ways may have unsatisfactory quality; therefore, an important step in image processing and analysis algorithms is a quality control stage of the received data. Poor quality images can be automatically deleted. In this article we study the problem of the automatic sharpness evaluation of digital images. As a result of the scientific literature analysis, 28 functions were selected that are used to analyze the clarity of digital images by calculation local estimates. All the functions first calculate local estimates in the neighborhood of every pixel, and then use the arithmetic mean as a generalized quality index. Testing have demonstrated that many estimates of local sharpness of the image often have abnormal distribution of the data. Therefore, some modified versions of the studied functions were additionally evaluated, instead of the average of local estimates, we studied the Weibull distribution parameters (FORM, SCALE, MEAN weib, MEDIAN weib). We evaluated three variants of the correlation of quantitative sharpness assessments with the subjective assessments of human experts. Since distribution of local features is abnormal, Spearman and Kendall rank correlation coefficients were used. Correlation above 0.7 means good agreement between quantitative and visual estimates. The experiments were carried out on digital images of various quality and clarity: artificially blurred images and blurred during shooting. Summing up results of the experiments, we propose to use seven functions for automatic analysis of the digital image sharpness, which are fast calculated and better correlated with the subjective sharpness evaluation.https://doklady.bsuir.by/jour/article/view/2178image quality assessmentimage sharpnessblurnormal distributionweibull distribution |
| spellingShingle | Y. I. Golub F. V. Starovoitov V. V. Starovoitov COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki image quality assessment image sharpness blur normal distribution weibull distribution |
| title | COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT |
| title_full | COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT |
| title_fullStr | COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT |
| title_full_unstemmed | COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT |
| title_short | COMPARATIVE ANALYSIS OF NO-REFERENCE MEASURES FOR DIGITAL IMAGE SHARPNESS ASSESSMENT |
| title_sort | comparative analysis of no reference measures for digital image sharpness assessment |
| topic | image quality assessment image sharpness blur normal distribution weibull distribution |
| url | https://doklady.bsuir.by/jour/article/view/2178 |
| work_keys_str_mv | AT yigolub comparativeanalysisofnoreferencemeasuresfordigitalimagesharpnessassessment AT fvstarovoitov comparativeanalysisofnoreferencemeasuresfordigitalimagesharpnessassessment AT vvstarovoitov comparativeanalysisofnoreferencemeasuresfordigitalimagesharpnessassessment |