Non-destructive Detection Of Ready-to-Eat Sea Cucumber Freshness Based On Hyperspectral Imaging

Ready-to-eat sea cucumber has a high nutritional value,medicinal valu,easier to eat.But,sea cucumber is perishable in the processing,transportation,sale due to the unique biological characteristics.Freshness is a key index for quality regulation and assurance during the processing and storage of ready-to-eat sea cucumbers.The usual freshness detection methods,sensory evaluation and physicochemical detection,are inadequate for mass,standardized and industrial production.In this study,a nondestructive freshness detection method based on hyperspectral imaging was proposed for ready-to-eat sea cucumbers.The main research contents are as follows:1、The Total Volatile Basic Nitrogen value of the sample was extracted from the TVB-N detector.It was used as critetion of,modeling.Ready-to-eat sea cucumber hyperspectral images were clollected by hyperspectral system,and the black and white correction method was used to eliminate the elimination of instrument interference.2、The effective dimensional-reduction method was adopted to address the massive data of hyperspectral images.According to the spectral absorption characteristics of the sea cucumber body wall,the wavelengths with significant chemical absorption characteristics were used as dividing points for band division.Thus,five sub-bands and the full band were acquired for data processing.Next,the bands were optimized using Image Principle Component Analysis(IPCA),and based on the calculated weight coefficients,the band-ratio image was selected as the characteristic image.3、The characteristic image.processing method of band ratio,bilateral filteing,improvediterative algorithm segmentation based on connected region and seed filling,mask algorithm was studied,On that basis,the gray-gradient co-occurrence matrix(GGCM)was used to extract entropy,correlation,moment of inertia and energy;the gray-level co-occurrence matrix(GLCM)was used to extract gradient distribution heterogeneity,energy,deficit moment,gray scale heterogeneity and small gradient..Equivalent to rotation invariance texture with local binary pattern(LBP)extracte ten texture features.4、Meanwhile,the measured total volatile basic nitrogen(TVB-N)contents were used as the criterion.Using these three types of texture features as the input data,three freshness evaluation models based on particle swarm optimization(PSO)and back propagation neural network(BPNN)were established.The detection accuracies of these three models are 90%,95%,and 80%.5、Based on the above study,the software system was builded for non-destructive detection of ready-to-eat sea cucumber freshness,including testing,integrated filtering denoising,threshold segmentation,texture extraction,model establishment and other functions,which can be used to facilitate the pretreatment of hyperspectral ready-to-use sea cucumber images and grade for freshness of ready-to-eat sea cucumber.