Abstract: An automated guided vehicle (AGV) has an image reader that scans indicia located on a floor. The image reader scan the indicium to obtain instructions for the AGV to follow. A processor in the AGV can perform geometry estimation of ellipsoidal objects in order to align the AGV as it moves or is stopped along a path.

Abstract: The disclosure relates to a data reading system and method for obtaining target data from an image. The data reading method includes obtaining an image containing the target data, and identifying a starting pixel coordinate on the image. The method further includes determining an initial local threshold value based on the selected starting pixel and analyzing the image to detect one or more high contrast boundaries or contours. After detecting the boundaries, the method includes analyzing the one or more boundaries to identify the target data in the image.

Abstract: An automated guided vehicle (AGV) has an image reader that scans indicia located on a floor. The image reader scan the indicium to obtain instructions for the AGV to follow. A processor in the AGV can perform geometry estimation of ellipsoidal objects in order to align the AGV as it moves or is stopped along a path.

Abstract: A system and method for processing imaged machine readable indicia may include capturing an image of a machine readable indicia including multiple codewords. A determination of an actual scanline of a codeword of the captured indicia may be made. A virtual scanline of the codeword of the imaged indicia for a type of symbology may be generated. In response to the virtual and actual scanlines matching, data representative of the codeword may be stored. Otherwise, repeat generating virtual scanlines of the codewords and compare the generated virtual scanlines with the actual scanlines until a match is identified or possible virtual codewords are exhausted. In response to a match, data representative of the matched scanline may be stored. The process may further repeatedly determine, generate, and compare until each codeword is determined. Data represented by the indicia based on the stored data representative of the matched codewords may be generated.

Abstract: The disclosure relates to a data reading system and method for obtaining target data from an image. The data reading method includes obtaining an image containing the target data, and identifying a starting pixel coordinate on the image. The method further includes determining an initial local threshold value based on the selected starting pixel and analyzing the image to detect one or more high contrast boundaries or contours. After detecting the boundaries, the method includes analyzing the one or more boundaries to identify the target data in the image.

Abstract: A system and method for processing imaged machine readable indicia may include capturing an image of a machine readable indicia including multiple codewords. A determination of an actual scanline of a codeword of the captured indicia may be made. A virtual scanline of the codeword of the imaged indicia for a type of symbology may be generated. In response to the virtual and actual scanlines matching, data representative of the codeword may be stored. Otherwise, repeat generating virtual scanlines of the codewords and compare the generated virtual scanlines with the actual scanlines until a match is identified or possible virtual codewords are exhausted. In response to a match, data representative of the matched scanline may be stored. The process may further repeatedly determine, generate, and compare until each codeword is determined. Data represented by the indicia based on the stored data representative of the matched codewords may be generated.

Abstract: Systems and methods for processing images to recognize characters. Such may include locating background in an image which separate lines of characters, and then locating background which separate characters. The inter-character spaces within a line may be used to determine a probable inter-character spacing for the characters. Within each detected line, the character having an inter-character spacing most similar to the probable inter-character spacing may be set as a starting character for classification. Using the probable inter-character spacing and the location of the starting character, the location of a character adjacent to the starting character in a first direction may be determined and the character classified. Such process may repeat in the first direction until a first end of the line is reached. The process may then move to a character adjacent the starting character in a second direction and repeat until a second end of the line is reached.

Abstract: Systems and methods for processing images to recognize characters. Such may include locating background in an image which separate lines of characters, and then locating background which separate characters. The inter-character spaces within a line may be used to determine a probable inter-character spacing for the characters. Within each detected line, the character having an inter-character spacing most similar to the probable inter-character spacing may be set as a starting character for classification. Using the probable inter-character spacing and the location of the starting character, the location of a character adjacent to the starting character in a first direction may be determined and the character classified. Such process may repeat in the first direction until a first end of the line is reached. The process may then move to a character adjacent the starting character in a second direction and repeat until a second end of the line is reached.

Abstract: A method includes identifying a set of functional parameters that are settable for processing the image and a plurality of instances of the set of functional parameters. A different mode for processing this image corresponds to each of these instances. The method includes selecting a determined processing mode for decoding the optical information from the processing modes of a working set of processing modes, and applying this selected processing mode and further comprises associating with each processing mode a respective probability of success. Selecting one of the methods of the working set includes choosing the processing mode with the highest value of probability of success and updating after each application of the selected processing mode, both if the decoding was successful and if the decoding was not successful, the probability of success of each processing mode of the working set, such as to perform adaptive decoding of the optical information.

Abstract: Systems and methods for robust recognition of machine-readable symbols from highly blurred or distorted images. An image signal representation of a machine-readable symbol element is transformed into a different space using one or more transform operations, which moves an n-dimensional vector of measured light intensities into another n-dimensional space. The types of transform operations may include blur robust orthonormal bases, such as the Discrete Sine Transform, the Discrete Cosine Transform, the Chebyshev Transform, and the Lagrange Transform. A trained classifier (e.g., an artificial intelligence machine learning algorithm) may be used to classify the transformed signal in the transformed space. The types of trainable classifiers that may be used include random forest classifiers, Mahalanobis classifiers, support vector machines, and classification or regression trees.

Abstract: Systems and methods for robust recognition of machine-readable symbols from highly blurred or distorted images. An image signal representation of a machine-readable symbol element is transformed into a different space using one or more transform operations, which moves an n-dimensional vector of measured light intensities into another n-dimensional space. The types of transform operations may include blur robust orthonormal bases, such as the Discrete Sine Transform, the Discrete Cosine Transform, the Chebyshev Transform, and the Lagrange Transform. A trained classifier (e.g., an artificial intelligence machine learning algorithm) may be used to classify the transformed signal in the transformed space. The types of trainable classifiers that may be used include random forest classifiers, Mahalanobis classifiers, support vector machines, and classification or regression trees.

Abstract: A method includes identifying a set of functional parameters that are settable for processing the image and a plurality of instances of the set of functional parameters. A different mode for processing this image corresponds to each of these instances. The method includes selecting a determined processing mode for decoding the optical information from the processing modes of a working set of processing modes, and applying this selected processing mode and further comprises associating with each processing mode a respective probability of success. Selecting one of the methods of the working set includes choosing the processing mode with the highest value of probability of success and updating after each application of the selected processing mode, both if the decoding was successful and if the decoding was not successful, the probability of success of each processing mode of the working set, such as to perform adaptive decoding of the optical information.

Abstract: A barcode decoding method includes obtaining a plurality of scanning lines defining a second set of scanning lines which also comprises a predetermined scanning line. Each scanning line has a first set of pixels, each identified by a first and by a second index. The pixels that are part of the second set of scanning lines define a third set of pixels and, from the pixels of the third set of pixels, it is possible to select a fourth set of pixels to construct an oversampled profile of the barcode, ordering intensity values calculated from the intensity values of the pixels of the fourth set. The pixels of the fourth set include pixels of the predetermined scanning line and further pixels of the third set that do not belong to the predetermined scanning line, to obtain a subpixel resolution that is able to decode the barcode.

Abstract: A method for decoding a two-dimensional optical code formed by a set number of codewords, wherein decoding the code based on a single acquired image has not been successful, includes analyzing an acquired image and at least one further acquired image and obtaining a respective set and further set of values of identified codewords. Each codeword can take on either an undefined value or vice versa a numeric value if the codeword is recognized. A combined set of codewords is created and each codeword of the combined set is assigned a value of a codeword of the set and/or of the further set and an algorithm for detecting and self-correction of errors is applied to the combined set to obtain confirmation of successful decoding of the two-dimensional code.

Abstract: A method for decoding a two-dimensional optical code formed by a set number of codewords, wherein decoding the code based on a single acquired image has not been successful, includes analysing an acquired image and at least one further acquired image and obtaining a respective set and further set of values of identified codewords. Each codeword can take on either an undefined value or vice versa a numeric value if the codeword is recognised. A combined set of codewords is created and each codeword of the combined set is assigned a value of a codeword of the set and/or of the further set and an algorithm for detecting and self-correction of errors is applied to the combined set to obtain confirmation of successful decoding of the two-dimensional code.

Abstract: A barcode decoding method includes obtaining a plurality of scanning lines defining a second set of scanning lines which also comprises a predetermined scanning line. Each scanning line has a first set of pixels, each identified by a first and by a second index. The pixels that are part of the second set of scanning lines define a third set of pixels and, from the pixels of the third set of pixels, it is possible to select a fourth set of pixels to construct an oversampled profile of the barcode, ordering intensity values calculated from the intensity values of the pixels of the fourth set. The pixels of the fourth set include pixels of the predetermined scanning line and further pixels of the third set that do not belong to the predetermined scanning line, to obtain a subpixel resolution that is able to decode the barcode.