An IoT based apparatus to assess the quality of food or agricultural produce is disclosed. The apparatus comprises a frame having an enclosure, a movable tray disposed at a middle portion of the enclosure, one or more camera installed within the enclosure, one or more light source strategically mounted within the enclosure to avoid reflection and hot spots, at least one storage unit, a touch screen display and a single board computer coupled to the camera, light source, storage unit and touch screen display. The enclosure is illuminated by the light source and the camera is configured to capture the image of the produce from both the top and bottom side of the produce. A pre-trained deep learning model is used on both the top and bottom view images to identify defects in the agricultural produce. The identified defects are displayed to the user via the touch screen display.