Jasmine flowers color degradation through user-coded computer vision image analysis tool

Authors: TAZEEN, HUMEERA - North Dakota State University; JOICE, ASTINA - North Dakota State University; TUFAIQUE, TALHA - North Dakota State University; IGATHINATHANE, C. - North Dakota State University; AJAYI-BANJI, A. - North Dakota State University; ZHANG, Z. - North Dakota State University; Whippo, Craig; Scott, Drew; Hendrickson, John; Archer, David; Pordesimo, Lester; SOKHANSANJ, S. - University Of British Columbia

Submitted to: Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/12/2025
Publication Date: 6/16/2025
Citation: Tazeen, H., Joice, A., Tufaique, T., Igathinathane, C., Ajayi-Banji, A., Zhang, Z., Whippo, C.W., Scott, D.A., Hendrickson, J.R., Archer, D.W., Pordesimo, L.O., Sokhansanj, S. 2025. Jasmine flowers color degradation through user-coded computer vision image analysis tool. Agriculture. 7(6):193. https://doi.org/10.3390/agriengineering7060193.
DOI: https://doi.org/10.3390/agriengineering7060193

Interpretive Summary: Jasmine flowers are valued for their fragrance and essential oils. They are used in flavor, cosmetics, and pharmaceutical industries. However, their useful life is short since their color can rapidly degrade due to environmental factors like light, temperature, and humidity. Therefore, measuring color variation and degradation over time is important to evaluate the shelf life for jasmine flowers. Manual methods for accurate color measurement are time consuming, so computer vision analysis was used in this research. Java-based open-source ImageJ software was employed to develop a plugin program that quantifies separately the color degradation of jasmine petals and pedicels over 25 hours. Color indices were fitted using statistical models. Results for jasmine petals indicated the most suitable color degradation indices are 'E, CIVE, and VEG, and the Peleg kinetic model had the best fit for most color indices. Whereas jasmine pedicels showed faster color degradation, best described by the hue index. Study results indicate that jasmine petals retained their color longer than pedicels. This was likely due to their higher pigment concentrations and structural characteristics. This study underscores the potential for using computer vision analysis and kinetic modeling to evaluate flower quality after harvest. Kinetic models accurately characterized color degradation dynamics. These results provide insights that can be used by producers and processors to improve storage and handling practices.

Technical Abstract: Jasmine (Jasminum sambac (L.) Ait.) flowers, valued for their fragrance and essential oils, are extensively used in industries such as flavor, cosmetics, and pharmaceuticals. However, their useful life is short due to rapid color degradation and browning caused by photo-oxidative stress induced by environmental factors like light, temperature, and humidity. Therefore, the significant reduction in the visual appeal, quality, and economic value necessitates the measurement of temporal color variation and quantification of color degradation to evaluate the shelf life for jasmine flowers. While manual methods for accurate color measurement and its variation over time are cumbersome and not feasible, computer vision analysis has been employed in this research. A Java-based open-source ImageJ software was employed to develop a plugin program that quantifies separately the color degradation of jasmine petals and pedicels over 25 h. Various color indices, including total color difference ('E), hue, chroma, browning index, color index of vegetation extraction (CIVE), and vegetative index (VEG), were fitted using kinetic models, including zeroth-order, first-order, exponential decay, Page, and Peleg. Model performances were evaluated using coefficient of determination (R2), root mean square error (RMSE), Akaike information criteria (AIC) and Bayesian information criteria (BIC). Analyzed results for jasmine petals indicated the most suitable color degradation indices are 'E, CIVE, and VEG, and the Peleg kinetic model exhibited the best fit for most color indices (R2 = 0.99). Whereas jasmine pedicels exhibited faster color degradation, best described by the hue index (R2 = 0.99). Study results indicate that jasmine petals retained their color integrity for longer periods than pedicels, attributable to their higher pigment concentrations and structural characteristics. This study underscores the potential of computer vision analysis and kinetic modeling for evaluating flower quality after harvest. By integrating kinetic models, the color degradation dynamics were accurately characterized, providing actionable insights for optimizing storage and handling practices.