A method may include obtaining a dataset including a target Action Unit (AU) combination and labeled images of the target AU combination with at least a first category of intensity for each AU of the target AU combination and a second category of intensity for each AU of the target AU combination. The method may also include determining that the first category of intensity for a first AU has a higher number of labeled images than the second category of intensity for the first AU, and based on the determination, identifying a number of new images to be synthesized in the second category of intensity for the first AU. The method may additionally include synthesizing the number of new images with the second category of intensity for the first AU, and adding the new images to the dataset.

When a user designates a region of interest for a plurality of groups targeted for difference analysis in a microscopic observation image of a sample, an m/z candidate search unit (32) searches for candidates for m/z presumed to differ, based on collected mass spectral data. An intensity histogram creation unit processing unit (33) creates and displays a graph showing a frequency distribution of peak intensities at measurement points included in the region of interest of the groups for each of the m/z candidates. If this graph exhibits multimodality, the data distribution is not suitable for a statistical hypothesis test. Thus, an intensity range determination unit (34) limits an intensity range in accordance with a user's instruction. Then, an ROI correction unit (35) corrects the ROI so as to include only measurement points with peak intensities within the limited intensity range. After that, a test processing unit (36) performs a statistical hypothesis test by using the data corresponding to the corrected ROI. In this way, even if first user's setting of a region of interest is improperly made, it is possible to perform highly reliable difference analysis.

A method may include obtaining core image data regarding a geological region of interest. The method may further include obtaining well log data regarding the geological region of interest from one or more wells. The method may further include determining a sliding window that corresponds to a predetermined window size. The method may further include determining various quantitative image attributes using the core image data, the well log data, and the sliding window. The quantitative image attributes may be determined in a continuous manner by moving the sliding window along the core image data. The method may further include generating predicted rock data for the geological region of interest using the quantitative image attributes, a machine-learning algorithm, and a machine-learning model.

Disclosed is an image analysis method implemented by a computer, the method including analyzing a partial image which is a part of an image of a planar subject, generating partial-image analysis data representing a characteristic of the partial image, comparing, for each of a plurality of images, candidate-image analysis data with the partial-image analysis data, the candidate-image analysis data representing a characteristic of each of the plurality of images, and selecting a candidate image among the plurality of images, the candidate image including a part corresponding to the partial image.

A pulse wave detection device detects the face from a frame image and corrects the brightness of the face in accordance with the size of the face surface to appropriately detect a pulse wave even if brightness is changed due to movement of a subject with respect to lighting. The brightness of the face depends on the distance between the lighting and the face, and this is equal to indirect measurement of the distance from the lighting to the face using the size of the face. As described above, a pulse wave detecting device estimates/measures a pulse rate of the subject from a brightness signal after intensity of the brightness of the face photographed on the frame image is corrected using the size of the face, by using the correlation between the size of the face of the subject on the frame image and the brightness of the face.

An image classification method and apparatus, and a style transfer model training method and apparatus are provided, which are relate to the field of deep learning, cloud computing and computer vision in artificial intelligence. The image classification method comprises: inputting an image of a first style into a style transfer model, to obtain an image of a second style corresponding to the image of the first style; and inputting the image of the second style into an image classification model, to obtain a classification result of the image of the second style, wherein the style transfer model is obtained through training on the basis of a sample image of the first style and a sample image of the second style; and the image classification model is obtained through training on the basis of the sample image of the second style.

An image processing apparatus includes an identifiability value obtaining portion, an inspection region generation portion, and an image inspection portion. The identifiability value obtaining portion is configured to obtain, for each pixel address constituting an image plane, an identifiability value for identifying which of a first inspection result and a second inspection result the pixel address corresponds to. The inspection region generation portion is configured to generate an inspection region serving as a target of image processing by setting a portion of the image plane including the pixel address where the obtained identifiability value satisfies a specific condition as the inspection region. The image inspection portion is configured to perform image processing for inspection on a partial image corresponding to the inspection region among a third image obtained by imaging a third target object.

An apparatus for image conversion includes a processor configured to classify a reference region representing a predetermined feature into a shadowed region and an unshadowed region, the reference region being in an aerial image represented in RGB color space; determine a tone correction factor so that a difference between an average luminance of the shadowed region and an average luminance of the unshadowed region in the aerial image represented in predetermined color space to which the color space of the aerial image is converted from RGB color space is less than a difference between an average luminance of the shadowed region and an average luminance of the unshadowed region represented in RGB color space; correct tones of the aerial image with the tone correction factor; and convert the color space of the aerial image from RGB color space to the predetermined color space to generate a color conversion image.

Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.

A method and a system of detecting at least one sample in a sample container, comprising a sample container, further comprising a cavity, the volume of said cavity partially or fully occupied with at least one solid sample and at least one fluid; and at least one camera capturing at least one image of the sample container; and a data processing device detecting at least one sample in the sample container by processing the at least one image captured by the at least one camera. The method and system further comprise putting the sample container in sudden motion prior to the at least one camera capturing at least one image of the sample container.