To suppress an increase in processing time due to a load of inference processing while improving reading accuracy by the inference processing of machine learning. An optical information reading device includes a processor including: an inference processing part that inputs a code image to a neural network and executes inference processing of generating an ideal image corresponding to the code image; and a decoding processing part that executes first decoding processing of decoding the code image and second decoding processing of decoding the ideal image generated by the inference processing part. The processor executes the inference processing and the first decoding processing in parallel, and executes the second decoding processing after completion of the inference processing.

A computer implemented method for detecting and reading a barcode in an image of a marked glass substrate, the method taking as input a raster image of at least one portion of the marked glass substrate and providing as output an abstract image of the barcode, the method including (a) computing a probability occurrence ? of the barcode in the raster image with a first trained convolutional artificial neural network; (b) computing coordinates of representative points of a boundary of the barcode in the raster image-according to a given threshold ? for the probability occurrence ? computed at (a); (c) cropping the raster image to the boundary of the barcode according to the coordinates computed at (b), and (d) computing with a second trained convolutional artificial neural network a tensor of probabilities for each pixel of the cropped raster image, the tensor being the abstract image of the barcode.

A system for verifying a machine-readable label comprises a scan table processing device comprising a first input for receiving a list of items with machine-readable labels; a second input for receiving a list of stores that have an inventory of the items in the list of items and that have at least one sensing device for capturing images of the items; and an output that includes a plurality of electronic records. The system further comprises a data repository that stores the captured images of the items and that updates the electronic records to include an association to the captured images; a graphical user interface (GUI) processing apparatus that modifies the captured images in preparation for training an artificial intelligence apparatus to identify the items in the images; and a machine language (ML) model processor that determines whether the images training the artificial intelligence apparatus are correctly identified with machine-readable labels associated with the items.

The disclosure includes a fixed retail scanner including a data reader, comprising a main board including one or more processors including a system processor, one or more camera modules, and an artificial intelligence (AI). The system processor is configured to transmit image data received from the one or more camera modules responsive to one or more event triggers detected by the system processor, and wherein the AI accelerator is configured to perform analysis based on an AI engine local to the AI accelerator in response to the event trigger. A remote server may also be operably coupled to the fixed retail scanner through the multi-port network switch, the remote server having a remote AI engine stored therein, wherein the local AI engine within the fixed retail scanner is a simplified AI model relative to the remote AI engine within the remote server.

Methods, apparatuses and computer program products for providing artificial-intelligence-based indicia data editing are provided. For example, an example computer-implemented method may include determining, based at least in part on a data processing model associated with a scan setting module, a first decoded data string corresponding to a first indicia; determining, based at least in part on user input data, a first input data string corresponding to the first indicia; generating a predictive indicia data editing model based at least in part on providing the first decoded data string and the first input data string to an artificial intelligence algorithm; and updating the scan setting module based at least in part on the predictive indicia data editing model.

A method of locating code image zones in an output image of a code bearing object (14), wherein first candidates for code image zones are determined in a first segmentation process using a process of classical image processing without machine learning and second candidates for code image zones are determined in a second segmentation process using machine learning, with the first and second candidates being fused to locate the code image zones.

A method includes: capturing an image; partitioning the image into sub-images; for each sub-image: providing the sub-image to a detection model, receiving, from the detection model, one or more sub-image regions of interest (SROIs), each SROI defined by (i) a position of the SROI, and (ii) one of a set of symbology categories, each symbology category encompassing a plurality of barcode symbologies; generating one or more regions of interest (ROI) from the SROIs, each ROI defined by a position of the ROI in the image, and a symbology category; and providing the ROIs to a decoder.

The disclosure includes a fixed retail scanner including a data reader, comprising a main board including one or more processors including a system processor, one or more camera modules, and an artificial intelligence (AI). The system processor is configured to transmit image data received from the one or more camera modules responsive to one or more event triggers detected by the system processor, and wherein the AI accelerator is configured to perform analysis based on an AI engine local to the AI accelerator in response to the event trigger. A remote server may also be operably coupled to the fixed retail scanner through the multi-port network switch, the remote server having a remote AI engine stored therein, wherein the local AI engine within the fixed retail scanner is a simplified AI model relative to the remote AI engine within the remote server.

A method for traceability of raw materials or objects exposed to operational conditions in industry, including coding phasea and decoding phase. The coding phase includes steps of uploading a design matrix file to a Cdot API, the Cdot matrix is a digital decomposition part of the coding phase, coding parameter inputs of the design matrix; generating a Cdot matrix by embedding a codeword using a Cdot matrix calculation algorithm. The decoding phase includes providing the Cdot matrix to a reader device; creating a Cdot matrix image from a raw image of a material or object or product having a Cdot matrix on a surface captured by a camera; decoding coded values in a code area of the Cdot matrix image to extract an assertive code; interpreting the assertive code to determine a unique object or material identification definition; providing the the object or material identification definition to a display.

A method for reading a one-dimensional optical code, wherein image data including the code are captured and a plurality of grayscale value profiles through the code are obtained from the image data, a black-and-white profile is formed from the grayscale value profiles by binarization, and the code content of the code is read from the black-and-white profile, wherein, for preparing the binarization, a sharpened grayscale value profile is first generated from the plurality of grayscale value profiles, the sharpened grayscale value profile having, as compared to the original image data, increased resolution, sharper edges, and more pronounced extrema, and the sharpened grayscale value profile is binarized to form the black-and-white profile.