Abstract: Local image enhancement processing is executed on an image obtained by imaging a transcription material. The enhanced image is divided into a plurality of patch images and input to a machine learning identifier. The patch images after segmentation output from the machine learning identifier are combined to generate a likelihood map image of skin ridges from the whole image based on a result of the segmentation. Binarization processing is executed on the likelihood map image to generate a binary image. A skin ridge region is extracted based on the binary image to calculate the area of the skin ridge region.

Abstract: Provided is a technique for preventing erroneous recognition of a fine particle region from a captured image of fine particles. A fine particle testing apparatus of the present disclosure includes: an imaging part capturing a first fine particle image of a well that holds a liquid containing fine particles; an image processor executing a process of generating a second fine particle image by extracting a contour of the first fine particle image, a process of performing a logical operation between the first fine particle image and the second fine particle image, a process of calculating a feature amount of the fine particles based on a result of the logical operation, and a process of determining growth of the fine particles in the well based on the calculated feature amount; and an output part outputting a result of the determination.

Abstract: Provided is a technique that enables accurate determination as to whether growth of bacteria has occurred or been inhibited. A bacteria test apparatus according to the present disclosure includes a microscope optical system which captures images of bacteria in each of a plurality of wells at a plurality of time points, the plurality of wells each holding a culture solution containing an antibacterial drug and the bacteria, an arithmetic unit which calculates a feature of luminance value for each of the images of the bacteria, a determination unit which determines whether growth of the bacteria has occurred in the wells based on a change in the feature of luminance value, and a display device which displays a determination result output from the determination unit. The arithmetic unit calculates, as the feature of luminance value, a feature including at least one of a mean, a median, or a mode (see FIG. 4).

Abstract: An endoscopic image diagnosis support system (100) includes: a memory (10) that stores learning images pre-classified into pathological types; and a processor (20) that, given an endoscopic image, performs feature value matching between an image of an identification target region in the endoscopic image and the learning images, to identify the pathological types in the identification target region.

Abstract: In a symbol recognition device, each histogram computation module receives an image of each partial region of a recognition target region in a binarized image and computes a frequency distribution of pixels of a given color in each line or column in the partial region; each run length determination module receives an image of each partial region of the recognition target region and determines whether or not a line or column of pixels of the given color having a certain length is present in the partial region; a control module feeds pixel information of the partial regions, read by scanning the binarized image stored in the image memory, into the histogram computation modules and the run length determination modules; a determination module determines a symbol included in the binarized image based on computation results of the histogram computation modules and determination results of the run length determination modules.

Abstract: An endoscopic image diagnosis support system (100) includes: a memory (10) that stores learning images pre-classified into pathological types; and a processor (20) that, given an endoscopic image, performs feature value matching between an image of an identification target region in the endoscopic image and the learning images, to identify the pathological types in the identification target region.

Abstract: In a symbol recognition device, each histogram computation module receives an image of each partial region of a recognition target region in a binarized image and computes a frequency distribution of pixels of a given color in each line or column in the partial region; each run length determination module receives an image of each partial region of the recognition target region and determines whether or not a line or column of pixels of the given color having a certain length is present in the partial region; a control module feeds pixel information of the partial regions, read by scanning the binarized image stored in the image memory, into the histogram computation modules and the run length determination modules; a determination module determines a symbol included in the binarized image based on computation results of the histogram computation modules and determination results of the run length determination modules.

Abstract: An associative memory that can reduce search errors is provided. An associative memory includes R distance/time conversion circuits DT1 to DTR. The R distance/time conversion circuits DT1 to DTR each include a NAND circuit 40 and N bit stages 41 to 4k. The N bit stages 41 to 4k delay a signal from the NAND circuit 40 by longer delay time as the distance between reference data and search data is greater and oscillate the signal. Among R oscillation signals output from the distance/time conversion circuits DT1 to DTR, the earliest changing oscillation signal is detected as an oscillation signal for the Winner row.

Abstract: An associative memory capable of reducing erroneous searches is provided. A storage memory in the associative memory stores reference data. A comparator circuit receives externally applied search data and obtains the distance (for example, the Hamming distance) between the reference data and the search data. An oscillating circuit outputs a pulse signal with an oscillating frequency corresponding to the distance obtained by the comparator circuit. Similarly, the oscillating circuits output pulse signals with oscillating frequencies according to the distance between the reference data in corresponding storage circuits and the search data. A WTA circuit receives the pulse signals. Reference data stored in a storage circuit corresponding to an oscillating circuit that outputs a pulse signal with the highest frequency is determined as the most similar reference data (Winner) to the search data.

Abstract: An associative memory that can reduce search errors is provided. An associative memory includes R distance/time conversion circuits DT1 to DTR. The R distance/time conversion circuits DT1 to DTR each include a NAND circuit 40 and N bit stages 41 to 4k. The N bit stages 41 to 4k delay a signal from the NAND circuit 40 by longer delay time as the distance between reference data and search data is greater and oscillate the signal. Among R oscillation signals output from the distance/time conversion circuits DT1 to DTR, the earliest changing oscillation signal is detected as an oscillation signal for the Winner row.

Abstract: An offset removal circuit (10) includes a removal circuit (1) and a removal circuit (2). The removal circuit (1) digitally removes offset voltage from an input voltage Vin. The removal circuit (2) removes offset voltage, in an analog manner, from the voltage subjected to offset voltage removal by the removal circuit (1). Then, the removal circuit (2) outputs the voltage subjected to the offset voltage removal to a non-inverting input terminal of a differential amplifier (20).

Abstract: An associative memory capable of reducing erroneous searches is provided. A storage memory in the associative memory stores reference data. A comparator circuit receives externally applied search data and obtains the distance (for example, the Hamming distance) between the reference data and the search data. An oscillating circuit outputs a pulse signal with an oscillating frequency corresponding to the distance obtained by the comparator circuit. Similarly, the oscillating circuits output pulse signals with oscillating frequencies according to the distance between the reference data in corresponding storage circuits and the search data. A WTA circuit receives the pulse signals. Reference data stored in a storage circuit corresponding to an oscillating circuit that outputs a pulse signal with the highest frequency is determined as the most similar reference data (Winner) to the search data.

Abstract: Associative memories capable of outputting multiple reference data close to search data are provided. A memory array compares each of the multiple reference data with the search data in parallel and generates multiple comparison current signals representing the result of the comparison. A WLA converts the multiple comparison current signals into voltages. During the first cycle, the WLA detects the lowest voltage among the voltages as Winner and detects the remaining voltages as Loser. After the second cycle, based on feedback signals, the WLA detects all the voltages other than a voltage detected as Winner during the last preceding cycle, and detects the lowest voltage among the detected voltages as Winner and detects the remaining detected voltages as Loser. The WLA repeats these operations k times.

Abstract: The present invention is directed to a pattern recognition system in which new reference data to be added is efficiently learned. In the pattern recognition system, there is performed the calculation of distances equivalent to similarities between input data of a pattern search target and a plurality of reference data, and based on input data of a fixed number of times corresponding to the reference data set as a recognized winner, a gravity center thereof is calculated to optimize the reference data. Furthermore, a threshold value is changed to enlarge/reduce recognition areas, whereby erroneous recognition is prevented and a recognition rate is improved.

Abstract: A dividing unit divides respective symbol sequences of input data applied with zigzag scan and a run-length process into a plurality of subsets having similar frequencies of occurrence, depending on a difference in frequencies of occurrence. A table creating unit scans each subset and creates a Huffman coding table for each subset. A coding unit executes a process for performing Huffman coding on each subset by using the Huffman coding table created for the subset, for all of the subsets in the plurality of subsets.

Abstract: A pixel-value detecting circuit (1) detects RGB values of each pixel of an input image and outputs the detected RGB values to a connection weight determining circuit (2). When both of two adjacent pixels have achromatic color, the connection weight determining circuit (2) determines a first connection weight, which is a connection weight between the two pixels, by using only the RGB values. When one of the two pixels has achromatic color, the connection weight determining circuit (2) determines, as a connection weight, a second connection weight that is smaller than the first connection weight, by using the RGB values and saturations. When both of the two pixels have chromatic color, the connection weight determining circuit (2) determines, as a connection weight, a third connection weight that is greater than or equal to the first connection weight, by using the RGB values and hues.

Abstract: An offset removal circuit (10) includes a removal circuit (1) and a removal circuit (2). The removal circuit (1) digitally removes offset voltage from an input voltage Vin. The removal circuit (2) removes offset voltage, in an analog manner, from the voltage subjected to offset voltage removal by the removal circuit (1). Then, the removal circuit (2) outputs the voltage subjected to the offset voltage removal to a non-inverting input terminal of a differential amplifier (20).

Abstract: A pixel-value detecting circuit (1) detects RGB values of each pixel of an input image and outputs the detected RGB values to a connection weight determining circuit (2). When both of two adjacent pixels have achromatic color, the connection weight determining circuit (2) determines a first connection weight, which is a connection weight between the two pixels, by using only the RGB values. When one of the two pixels has achromatic color, the connection weight determining circuit (2) determines, as a connection weight, a second connection weight that is smaller than the first connection weight, by using the RGB values and saturations. When both of the two pixels have chromatic color, the connection weight determining circuit (2) determines, as a connection weight, a third connection weight that is greater than or equal to the first connection weight, by using the RGB values and hues.

Abstract: A dividing unit divides respective symbol sequences of input data applied with zigzag scan and a run-length process into a plurality of subsets having similar frequencies of occurrence, depending on a difference in frequencies of occurrence. A table creating unit scans each subset and creates a Huffman coding table for each subset. A coding unit executes a process for performing Huffman coding on each subset by using the Huffman coding table created for the subset, for all of the subsets in the plurality of subsets.

Abstract: A semiconductor device includes a decoder receiving first multiplier data of 3 bits indicating a multiplier to output a shift flag, an inversion flag, and an operation flag in accordance with Booth's algorithm, and a first partial product calculation unit receiving first multiplicand data of 2 bits indicating a multiplicand, a shift flag, an inversion flag, and an operation flag to select one of the higher order bit and lower order bit of the first multiplicand data based on the shift flag, invert or non-invert the selected bit based on the inversion flag, select one of the inverted or non-inverted data and data of a predetermined logic level based on the operation flag, and output the selected data as partial product data indicating the partial product of the first multiplier data and the first multiplicand data.