Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification
Quality assessment is one of the most common processes in the agri-food industry. Typically, this task involves the analysis of multiple views of the fruit. Generally speaking, analyzing these single views is a highly time-consuming operation. Moreover, there is usually significant overlap between c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5452 |
| _version_ | 1797415823274409984 |
|---|---|
| author | Antonio Albiol Carlos Sánchez de Merás Alberto Albiol Sara Hinojosa |
| author_facet | Antonio Albiol Carlos Sánchez de Merás Alberto Albiol Sara Hinojosa |
| author_sort | Antonio Albiol |
| collection | DOAJ |
| description | Quality assessment is one of the most common processes in the agri-food industry. Typically, this task involves the analysis of multiple views of the fruit. Generally speaking, analyzing these single views is a highly time-consuming operation. Moreover, there is usually significant overlap between consecutive views, so it might be necessary to provide a mechanism to cope with the redundancy and prevent the multiple counting of defect points. This paper presents a method to create surface maps of fruit from collections of views obtained when the piece is rotating. This single image map combines the information contained in the views, thus reducing the number of analysis operations and avoiding possible miscounts in the number of defects. After assigning each piece with a simple geometrical model, 3D rotation between consecutive views is estimated only from the captured images, without any further need for sensors or information about the conveyor. The fact that rotation is estimated directly from the views makes this novel methodology readily usable in high-throughput industrial inspection machines without any special hardware modification. As proof of this technique’s usefulness, an application is shown where maps have been used as input to a CNN to classify oranges into different categories. |
| first_indexed | 2024-03-09T05:55:07Z |
| format | Article |
| id | doaj.art-364c92c43d71439c8f213a4e03b38968 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:55:07Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-364c92c43d71439c8f213a4e03b389682023-12-03T12:13:59ZengMDPI AGSensors1424-82202022-07-012214545210.3390/s22145452Single Fusion Image from Collections of Fruit Views for Defect Detection and ClassificationAntonio Albiol0Carlos Sánchez de Merás1Alberto Albiol2Sara Hinojosa3Departamento de Comunicaciones, Universitat Politècnica de València, 46022 Valencia, SpainDepartamento de Comunicaciones, Universitat Politècnica de València, 46022 Valencia, SpainITEAM Research Institute, Universitat Politècnica de València, 46022 Valencia, SpainMultiscan Technologies SL, 03820 Cocentaina, SpainQuality assessment is one of the most common processes in the agri-food industry. Typically, this task involves the analysis of multiple views of the fruit. Generally speaking, analyzing these single views is a highly time-consuming operation. Moreover, there is usually significant overlap between consecutive views, so it might be necessary to provide a mechanism to cope with the redundancy and prevent the multiple counting of defect points. This paper presents a method to create surface maps of fruit from collections of views obtained when the piece is rotating. This single image map combines the information contained in the views, thus reducing the number of analysis operations and avoiding possible miscounts in the number of defects. After assigning each piece with a simple geometrical model, 3D rotation between consecutive views is estimated only from the captured images, without any further need for sensors or information about the conveyor. The fact that rotation is estimated directly from the views makes this novel methodology readily usable in high-throughput industrial inspection machines without any special hardware modification. As proof of this technique’s usefulness, an application is shown where maps have been used as input to a CNN to classify oranges into different categories.https://www.mdpi.com/1424-8220/22/14/54523Drotationmappingprojectionunwrappingquality assessment |
| spellingShingle | Antonio Albiol Carlos Sánchez de Merás Alberto Albiol Sara Hinojosa Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification Sensors 3D rotation mapping projection unwrapping quality assessment |
| title | Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification |
| title_full | Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification |
| title_fullStr | Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification |
| title_full_unstemmed | Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification |
| title_short | Single Fusion Image from Collections of Fruit Views for Defect Detection and Classification |
| title_sort | single fusion image from collections of fruit views for defect detection and classification |
| topic | 3D rotation mapping projection unwrapping quality assessment |
| url | https://www.mdpi.com/1424-8220/22/14/5452 |
| work_keys_str_mv | AT antonioalbiol singlefusionimagefromcollectionsoffruitviewsfordefectdetectionandclassification AT carlossanchezdemeras singlefusionimagefromcollectionsoffruitviewsfordefectdetectionandclassification AT albertoalbiol singlefusionimagefromcollectionsoffruitviewsfordefectdetectionandclassification AT sarahinojosa singlefusionimagefromcollectionsoffruitviewsfordefectdetectionandclassification |