Identification of tomato maturity based on multinomial logistic regression with kernel clustering by integrating color moments and physicochemical indices

摘要

The identification of tomato maturity is significant to extend the fruit shelf life and generate the scientific processing strategy. Tomato maturation is a gradual process, and the internal physicochemical characteristics are most related to maturity states. Merely choosing visual features to identify maturity would cause discriminant errors. This study designed a simple and effective identification method for tomato maturity by integrating color moments and physicochemical indices. The color moments were extracted by an adaptive K-means clustering image processing program, and firmness, soluble solid content and sensory evaluation were measured by professional techniques. The optimal multidimensional index set was formulated according to color moments and physicochemical indices simultaneously. To reduce the confusion between adjacent stages, a novel multinomial logistic regression with kernel clustering (MLRKC) method was designed to identify maturity, and the accuracy was 95.83% for tomato testing set. Moreover, the traditional image features set and some classic methods were applied to verify the performance of proposed method, respectively. Finally, the proposed method was applied to identify the tomatoes in the realistic circumstance. The identification results demonstrated satisfactory performances and promising applications of MLRKC method integrating color moments and physicochemical indices. Practical Applications Tomato is a climacteric fruit which could mature after harvesting. Identification tomato maturity stage is significant to decide the optimal transportation modes, inventory strategies and processing technology. Traditional methods for identifying tomato maturity were high-cost and complicated, which were inefficient for small-scale production. The method proposed in this study could simply the identification steps and reduce the operating cost, and also provide more accurate and valuable information. The investigated theoretical basis could be incorporated into the small farmers and small-scale food processing companies to achieve tomato precision processing with low additional costs.