Optimized imaging methods for species-level identification of food-contaminating beetles

Abstract

Identifying the exact species of pantry beetle responsible for food contamination, is imperative in assessing the risks associated with contamination scenarios. Each beetle species is known to have unique patterns on their hardened forewings (known as elytra) through which they can be identified. Currently, this is done through manual microanalysis of the insect or their fragments in contaminated food samples. We envision that the use of automated pattern analysis would expedite and scale up the identification process. However, such automation would require images to be captured in a consistent manner, thereby enabling the creation of large repositories of high-quality images. Presently, there is no standard imaging technique for capturing images of beetle elytra, which consequently means, there is no standard method of beetle species identification through elytral pattern analysis. This deficiency inspired us to optimize and standardize imaging methods, especially for food-contaminating beetles. For this endeavor, we chose multiple species of beetles belonging to different families or genera that have near-identical elytral patterns, and thus are difficult to identify correctly at the species level. Our optimized imaging method provides enhanced images such that the elytral patterns between individual species could easily be distinguished from each other, through visual observation. We believe such standardization is critical in developing automated species identification of pantry beetles and/or other insects. This eventually may lead to improved taxonomical classification, allowing for better management of food contamination and ecological conservation.

Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning

“…We elaborated on the details of sample collection, preparation, and imaging technique in our previous publications on imaging optimization (Bisgin et al, 2018;Wu et al, 2019;Bera et al, 2021). Briefly, we used 12 different pantry beetle species harvested from our in-house collection.…”

“…Unlike the older image set, which was subjected to varied magnification (in the 75-100× range) and two-point reflected light, we used a fixed magnification of 100× and transmitted light for this study. These amendments significantly reduced glare spots and other imaging artifacts, and drastically improved the clarity of elytral patterns (Bera et al, 2021). We used a Leica MC170HD camera to acquire the images with an image resolution set to 2,592 × 1,944 dpi (dots per inch, the highest resolution available).…”

“…Compared to the traditionally https://github.com/hbisgin/beetleCNN acquired image set, the optimized image set was devoid of such artifacts as glare spots and other surface anomalies. Details on the imaging improvements, described elsewhere, are beyond the scope of this discussion (Bera et al, 2021). This image set subsequently was processed to obtain the set of sub-images used for our model.…”

“…Our findings in our earlier studies led us to scrutinize the image set and observe that images lacking visual clarity due to the reflective glare of the elytra surface were more prone to misidentification. To remedy this, we amended the optical and imaging settings and optimized the imaging conditions to obtain a high-quality image set unaffected by artifacts and showing the finer details of an elytron (Bera et al, 2021). We hypothesized that using such a high-quality image set would help us achieve a near-perfect prediction accuracy in identifying each pantry beetle species.…”