Optimization of Lighting Parameters for Imaging with the Optical Identification Module

Hyperspectral analysis is a non-invasive method that reduces losses and improves fruit quality by accurately identifying defects during sorting. A key requirement for obtaining reliable data is stable, uniform illumination provided by specialized light sources with a controlled spectrum. The integration of such systems into automated production lines minimizes human error, increases productivity, and supports the sustainable development of the agricultural sector. (Research purpose) The study aims to substantiate the selection of parameters for the hyperspectrometer and the light source within the illumination system. (Materials and methods) The optical identification module used in this study consists of stepper motors, rack-and-pinion and screw drives with bearings, and a platform with rubber rollers, the speed of which is regulated by a three-phase motor powered through a frequency converter. The stand suspension can move both horizontally and vertically at a preset speed. SpecGrabber and CubeCreator software was used to collect and process data during scanning, enabling subsequent image analysis using Gelion software. (Results and discussion) A hyperspectrometer was selected for the identification module, and the main light sources for the illumination system were determined. (Conclusions) The calculated luminous flux is 934 watts per square meter, which falls within the sensitivity range of 100–1500 watts per square meter for the Complementary Metal-Oxide-Semiconductor (CMOS) detector. This confirms that the camera can capture hyperspectral data under the specified exposure and illumination conditions. It was determined that four halogen lamps should be installed in the illumination module, providing an illuminance level of 3010 lux. At this lighting level, reliable spectral graphs were obtained for both healthy and diseased fruit areas. Additionally, the short exposure time of 2.1 milliseconds per spectrometer frame resulted in a total scanning time of less than 2 seconds.

1. Kurbanov R.K., Tsench Yu.S., Zakharova N.I. The main trends in the development of aerial photography technology of agricultural lands. Agricultural Machinery and Technologies. 2025. Vol. 19. N1. 86-96. DOI: 10.22314/2073-7599-2025-19-1-86-95.

2. Ahalaya B.Kh., Tsench Yu.S., Mironova A.V. et al. Electric and mechanical fruit pickers. Selskiy Mechanizator. 2023. N5. 15-21 (In Russian). DOI: 10.47336/0131-7393-2023-5-15-21.

3. Blank V.A., Skidanov R.V., Doskolovich L.L. Investigation of a spectral lens for the formation of a normalized difference vegetation index NDVI0.705. Journal of Optical Technology. 2022. Vol. 89. N3. 20-27. DOI: 10.17586/1023-5086-2022-89-03-20-27.

4. Korotchenya V.M., Tsench Yu.S., Lobachevsky Ya.P. Development of types of agricultural technologies for the machine system. MachineryTechnical Service of. 2024. Vol. 62. N4. 136-148. DOI: 10.22314/2618-8287-2024-62-4-136-148.

5. Balabanov P.V., Zhirkova A.A., Chugunov M.V. et al. Detection of defects on apples using hyperspectral reflection visualization combining both vegetation index analysis and neural network. Journal of Physics: IOP. 2020. Vol. 1515 9 (In English). DOI: 10.1088/1742-6596/1515/3/032064.

6. Zhirkova A.A. Optoelectronic quality control of apples using methods of multidimensional statistical analysis in the frames of lean manufacturing approach. Quality Management, Transport and Information Security, Information Technologies. 2022. Vol. 67. 243-246 (In English). DOI: 10.1109/ITQMIS56172.2022.9976708.

7. Drozdov D. Supervisory Mutual augmentation of spectral sensing and machine learning for non-invasive detection of apple fruit damages. Horticulturae. 2023. Vol. 8. 2-13 (In English). DOI: 10.3390/horticulturae8121111.

8. Shurygin B.M., Smirnov I.G., Chilikin A.D. et al. Complementarity of spectral sensing and machine learning for noninvasive detection of damage to apple trees. Horticulturae. 2022. Vol. 8. 4-12 DOI: 10.3390/horticulturae8121111.

9. Wu A., Zhu Z., Ren T. Detection of apple defect using laser-induced light backscattering imaging and convolutional neural network. Computers & Electrical Engineering. 2020. Vol. 81. 4-6 (In English). DOI: 10.1016/j.compeleceng.2019.106454.

10. Fan S., Li J., Zhang Y., Tian X., Huang W. On line detection of defective apples using computer vision system combined with deep learning methods. Journal of Food Engineering. 2020. Vol. 286. 7-12 (In English). DOI: 10.1016/j. jfoodeng.2020.110102.

11. Huang Y., Lu R., Chen K. Detection of internal defect of apples by a multichannel Vis/NIR spectroscopic system. Postharvest Biology and Technology. 2020. Vol. 161. 7-14 (In English). DOI: 10.1016/j.postharvbio.2019.111065.

12. Tang Z., Chen Z., Li G., Hu Y Multicolor nitrogen dots for rapid detection of thiram and chlorpyrifos in fruit and vegetable samples. Analytica Chemical Acta. 2020. Vol. 1136. 72-81 (In English). DOI: 10.1016/j.aca.2020.08.038.

13. Firsov N.A., Podlipnov V.V., Ivliev N.A. et al. Neural network-aided classification of hyperspectral vegetation images with a training sample generated using an adaptive vegetation index. Computer Optics. 2021. Vol. 45. N6. 887-896. DOI: 10.18287/2412-6179-CO-1038.

14. Vanoli M., Van Beers R., Sadar N. Time- and spatially-resolved spectroscopy to determine the bulk optical properties of Braeburn apples after ripening in shelf life. Postharvest Biology and Technology. 2020. Vol. 168. 5-7 (In English). DOI: 10.1016/j.postharvbio.2020.111233.

15. Ali Shah S., Zeb A., Waqar S. Towards fruit maturity estimation using NIR spectroscopy. Infrared Physics & Technology. 2020. Vol. 111. 4-7 (In English). DOI: 10.1016/j.infrared.2020.103479.

16. Balabanov P.V., Divin A.G., Zhirkova A.A. Obtaining spectrograms for the surface areas of the control objects (apples), including intact and damaged zones, as well as for the surface of the conveyor on which the control objects are transported. National Association of Scientists. 2021. N36-2 (63). 17-19 (In Russian). EDN: RVHEDR.