Information about a drug-containing vessel is determined by capturing image data of the curved surface of a cylindrical portion of a drug-containing vessel. The image data is unfurled from around the curved surface, binarised, and a template matching algorithm employed to determine that the label information comprises candidate information about the vessel and/or the drug.

Techniques are disclosed for image feature representation. The techniques exhibit discriminative power that can be used in any number of classification tasks, and are particularly effective with respect to fine-grained image classification tasks. In an embodiment, a given image to be classified is divided into image patches. A vector is generated for each image patch. Each image patch vector is compared to the Gaussian mixture components (each mixture component is also a vector) of a Gaussian Mixture Model (GMM). Each such comparison generates a similarity score for each image patch vector. For each Gaussian mixture component, the image patch vectors associated with a similarity score that is too low are eliminated. The selectively pooled vectors from all the Gaussian mixture components are then concatenated to form the final image feature vector, which can be provided to a classifier so the given input image can be properly categorized.

A search area is set on a recognition target image, cutout areas are set at a plurality of positions in the search area, images corresponding to the plurality of set cutout areas are extracted, similarities of candidate characters obtained by comparison between the extracted images and dictionary data is weighted in accordance with the positions of the cutout areas. In such a manner, evaluation values of the candidate characters are obtained, and a candidate character with the highest evaluation value among the obtained candidate characters is output as a recognition result. Further, a search area relating to a next character is set based on position information about the cutout area corresponding to the recognition result.

Information about a drug-containing vessel is determined by capturing image data of the curved surface of a cylindrical portion of a drug-containing vessel. The image data is unfurled from around the curved surface, binarised, and a template matching algorithm employed to determine that the label information comprises candidate information about the vessel and/or the drug.

Techniques are disclosed for image feature representation. The techniques exhibit discriminative power that can be used in any number of classification tasks, and are particularly effective with respect to fine-grained image classification tasks. In an embodiment, a given image to be classified is divided into image patches. A vector is generated for each image patch. Each image patch vector is compared to the Gaussian mixture components (each mixture component is also a vector) of a Gaussian Mixture Model (GMM). Each such comparison generates a similarity score for each image patch vector. For each Gaussian mixture component, the image patch vectors associated with a similarity score that is too low are eliminated. The selectively pooled vectors from all the Gaussian mixture components are then concatenated to form the final image feature vector, which can be provided to a classifier so the given input image can be properly categorized.

Techniques are disclosed for image feature representation. The techniques exhibit discriminative power that can be used in any number of classification tasks, and are particularly effective with respect to fine-grained image classification tasks. In an embodiment, a given image to be classified is divided into image patches. A vector is generated for each image patch. Each image patch vector is compared to the Gaussian mixture components (each mixture component is also a vector) of a Gaussian Mixture Model (GMM). Each such comparison generates a similarity score for each image patch vector. For each Gaussian mixture component, the image patch vectors associated with a similarity score that is too low are eliminated. The selectively pooled vectors from all the Gaussian mixture components are then concatenated to form the final image feature vector, which can be provided to a classifier so the given input image can be properly categorized.

A search area is set on a recognition target image, cutout areas are set at a plurality of positions in the search area, images corresponding to the plurality of set cutout areas are extracted, similarities of candidate characters obtained by comparison between the extracted images and dictionary data is weighted in accordance with the positions of the cutout areas. In such a manner, evaluation values of the candidate characters are obtained, and a candidate character with the highest evaluation value among the obtained candidate characters is output as a recognition result. Further, a search area relating to a next character is set based on position information about the cutout area corresponding to the recognition result.