Non-destructive detection of defects in Zizphus jujube Mill cv.Lingwu changzao based on near-infrared hyperspectral imaging

Abstract: Zizphus jujube Mill cv.Lingwu changzao, as one of characteristic agricultural products in Ningxia, is favored by the broad consumer for its high nutritional value. However, the external quality of long jujube will affect directly its sale and storage. In the traditional detection method, it has several disadvantages such as time-consuming, laborious and low efficiency, etc. Hyperspectral imaging technique has become an important trend to employ nondestructive testing of fruit quality, because it simultaneously has the merit of spectral technique and imaging technique. In order to study an effective method for quickly detecting common defects (bruise, insect-infested and cracks) on jujube fruits, the methods of principal component analysis (PCA) on the optimal wavelengths combined with band ratio (BR) were applied to identify the crack, insect and bruised jujubes. In the first place, a total of 300 samples were placed in 4℃ refrigerator storage, including a set of 100 defective jujubes with cracks; a set of 100 insect-infested jujubes with a hole greater than 0.1 mm in diameter on each of the selected jujube's surfaces; a set of 50 bruised jujubes, which are normal jujubes dropped from 1 m and with the region of injury marked; a set of 50 intact jujubes, were picked out by hand-picked the way to randomly and manually collect from three orchards in Lingwu, China during the harvest period of 2013. Before measuring, the samples were kept overnight at room temperature (23℃). Secondly, the hyperspectral images of jujubes in the spectral region 918-1 678 nm were acquired for 300 jujube samples. Region of interests (ROIs) as an average spectral of various jujubes were obtained and the wavelengths in the spectral region of near-infrared reflection were analyzed and combined with PCA method to determine feature wavelengths by weighted coefficient. Intact jujubes were selecting four optimal wavelength (1 028, 1 109, 1 312, 1 449 nm) , crack jujubes were selecting seven optimal wavelength (1 031, 1 112, 1 225, 1 312, 1 392, 1 449, 1 461 nm) , bruised crack jujubes were selecting four optimal wavelength (1 025, 1 109, 1 312, 1 449 nm) , and insect-infested jujubes were selecting four optimal wavelength (1 034, 1 112, 1 312, 1 449 nm). Compared to principal component images of full wavelength, the model of principal component images based on important wavelengths was the best to further studies. Then, the PCA method was performed again based on important wavelengths and the plot of PC-1 was used to classify bruised, insect-infested, cracked and intact jujube fruits. The classification rate of intact, insect-infested, cracked and bruised jujubes in the spectral region of near-infrared reflection were 100%, 72%, 86%, 100%, respectively; In order to further improve the recognition rate, the band ratio method was utilized to distinguish the previously unidentified jujubes (insect-infested, cracked). For insect- infested jujubes, four optimal wavelength (1 034, 1 112, 1 312, 1 449 nm) were made band ratio each other and the band ratio of R1231/R1109 was thought as optimal band combination. For crack jujubes, seven optimal wavelength (1 031, 1 112, 1 225, 1 312, 1 392, 1 449, 1 461 nm) were made band ratio each other but the results was not ideal, so the method of band ratio was not applicable to crack jujubes. In a word, the classification rate of intact, insect-infested, crack and bruised jujubes in the spectral region of near-infrared reflection were 100%, 90%, 86%, 100%, respectively. The results showed that the band ratio algorithm had positive effect on insect-infested jujubes, but not to crack jujubes. The rest of jujubes could not be correctly identified because that some crack and insect-infested jujubes in the defect area was too small, resulting in unable to conduct normal recognition. The results proved that the capability of NIR hyperspectral imaging technology for identifying external defects of jujube was feasible, which would provide research basis for online detection of jujube quality using multi-spectral imaging technology.