Structured illumination reflectance imaging for enhanced detection of subsurface tissue bruising in apples

Authors: LI, RICHARD - Michigan State University; LU, YUZHEN - Michigan State University; Lu, Renfu

Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/19/2018
Publication Date: 5/1/2018
Citation: Li, R., Lu, Y., Lu, R. 2018. Structured illumination reflectance imaging for enhanced detection of subsurface tissue bruising in apples. Transactions of the ASABE. 61(3):809-819.

Interpretive Summary: Structured-illumination reflectance imaging (SIRI) is a new imaging modality for quality detection of horticultural and food products. Different from conventional diffuse, uniform illumination that is widely used in machine vision systems for food inspection, SIRI applies sinusoidal patterns of illumination with specific spatial frequencies for better control of light penetration in the fruit tissue to achieve enhanced detection of subsurface defects in food, such as bruising in apples. This research was aimed at detecting fresh bruises on apples, which are difficult to detect by conventional imaging methods, using a new SIRI system developed in our lab. Three groups of 20 apples each of 'Golden Delicious' and 'Delicious' variety were subjected to one of three levels of impact generated by a pendulum impacting device. Three phase-shifted images were taken, using the SIRI system for each of three spatial frequencies from the apples that had been bruised for 0-2, 4-6, and 24 hours. The acquired SIRI images were then decomposed into the direct component (DC) images, which are equivalent to the ones obtained under uniform illumination, and the alternating component (AC) images, which contain depth-specific information about the fruit tissue. Image processing algorithms were developed to analyze the AC and DC images for bruise detection. SIRI resulted in 70%-100% bruise detection accuracies, compared to 0-50% accuracies obtained under conventional uniform illumination. Better SIRI results were obtained for apples with bruises of 4-6 hours old after impact. The detection rate was, however, affected by the severity of bruising and spatial frequency, and proper selection of spatial frequency is thus critical for achieving accurate bruise detection results. This study has demonstrated the advantage of SIRI in detecting bruising defect in apples, and the technique is promising for enhanced detection of food quality and safety.

Technical Abstract: In this research, a structured illumination reflectance imaging (SIRI) system was used as a novel method for fresh bruise detection. The SIRI system projects sinusoidal patterns of illumination onto samples, and image demodulation is then used to recover depth-specific information through varying the spatial frequency of the illumination pattern. The capability of SIRI was demonstrated through the detection of artificially induced bruises on ‘Golden Delicious’ and ‘Delicious’ apples with varying levels of bruising. It was hypothesized that by confining the light penetration depth near the surface of each fruit, subsurface defects such as bruising should be more apparent under SIRI than conventional planar illumination imaging. Three phase-shifted reflectance images were acquired from 60 fruit each of 'Golden Delicious' and 'Delicious' variety at 0, 4-6 and 24 h after impact bruising for each of the four spatial frequencies (i.e., 0, 0.10, 0.15 and 0.25 cycles/mm). The reflectance images acquired by the system were then demodulated into an alternating component (AC) and direct component (DC), where the AC contained depth-specific information and the DC image represented the diffuse reflectance from the apple sample under uniform (or planar) illumination. Bruise detection algorithms were developed and applied to the demodulated AC images. The SIRI system achieved 70-100% bruise detection rates, compared to 0-50% detection rates under conventional planar illumination. Detection results were, however, influenced by both severity of bruising and bruise development after impact; better detection results were obtained when bruises were 4-6 h old. SIRI has demonstrated a superior capability of detecting fresh bruises, and it is promising as a new imaging modality for quality detection of agricultural products.