Product verification using OCR classification and Mondrian conformal prediction

Multimodal Fine-Grained Grocery Product Recognition Using Image and Ocr Text

“…Recognition of products is required for many types of automation solutions at grocery stores. This includes automatic checkout systems for the registration of products [11][12][13], the monitoring of availability and misplacement on store shelves [14][15][16], frictionless checkout where a camera system with the inclusion of other sensors in a store registers the pick of products by customers [17,18] and detection of barcode switches and other fraudulent actions at SCOs [8,19]. A figure showing examples of applications can be seen in Figure 1.…”

“…This approach has been proposed in two recent surveys (see [6,7]) and listed as an important research direction to improve fine-grained recognition of grocery products [6,7]. In fact, recent work has shown that using extracted textual data from packages as input to natural language processing (NLP) models results in a robust text classifier with high accuracy, see [8,9]. Furthermore, Wei et al [7] state that no specific datasets exist for fine-grained product recognition.…”

Designing a Real-Time-Based Optical Character Recognition to Detect ID Cards

“…The easier it is to separate characters from the background, the more refined the OCR smoothness and the better the source image quality. The implementation is carried out using the Python programming language and the Tensorflow learning library 2.0 [3],[4], [12]. An Intel i5 microprocessor laptop machine and 4G RAM were used to run the implemented code.…”

“…One method that is used by many people to read (detect and recognize) is OCR. OCR reading is the process of converting the image (image) of letters into ASCII characters that are recognized by the computer as an alternative to solutions based solely on image recognition [12][13] [14]. In Indonesia Government and non-governmental organizations, the OCR method has not been implemented yet to read text information from citizen ID cards, especially Indonesian ID cards.…”