35results about How to "Reduce memory space requirements" patented technology

A method for correcting image artifacts is proposed. The artifacts occur as a result of an anti scatter grid connected rigidly to an x-ray detector in recording three-dimensional image datasets. Two-dimensional projection images of an object are recorded from different recording geometries for reconstruction the three-dimensional image dataset. A calibration image is recorded for each recording geometry. An average image from all recorded calibration images is established. Subtraction images are established by subtracting the average image from the corresponding calibration images. Noise is removed from the subtraction images. The subtraction images and the average image are stored. A correction image is established for each recording geometry by addition of the subtraction image assigned to the recording geometry and of the average image and is used for correcting the projection image.

In a digital still camera, pixel values representing an image frame in a first format are stored in a memory. The pixel values of the image frame in the first format are converted to a second format. The pixel values in the second format are stored in the memory by overwriting at least a portion of the pixel values in the first format. Memory space is thus conserved by the overwriting, thereby requiring reduced memory for storage of pixel values in the digital still camera. The minimum delay (shot to shot interval) required between user-indicated image capture instances is also reduced.

A real-time preprocessing method and storage medium for video surveillance data, the method comprising: obtaining the minimum channel map, and calculating the downsampled dark primary color D down , after converting the video image into a grayscale image, sort in descending order according to the grayscale value of the pixels, select a certain proportion of high-brightness pixels, and use the average value as the global atmospheric light estimation A; for the downsampled dark primary color D down Perform filtering processing to enhance the local small value to obtain the optimized down-sampled dark primary color D filter ; to D filter Up-sampling to get the scattered light estimation of each position of the video, according to the preset fog imaging model, using the scattered light estimation S and the global atmospheric light estimation A to inversely solve the fog-free picture of the t-th frame. The present invention obtains the dark primary color of down-sampling, reduces the amount of calculation, improves the running time, and is filter Scattered light can be estimated by up-sampling in blocks, and fog-free images can be reversed by blocks, which reduces the demand for memory space and is more suitable for the situation of uneven equipment in the Internet of Things environment.

The invention discloses a method for clustering and integrating X-ray film image data, which includes the following steps: S01: after preprocessing the X-ray film image, obtain data from the image; S02: obtain the gray value of each point in the image The intensity value Gi, j is stored in the gray value matrix G, Gi, j represents the gray value of the i-th row and the j-th column point in the image; S03: Use the clustering integration algorithm based on the K-means improved algorithm or the hierarchical clustering The improved algorithm performs clustering analysis processing on the gray value matrix G; S04: Use the HGPA algorithm to perform integrated operations. The clustering integration algorithm based on the K-means improved algorithm improves the selection of K initial cluster centers. The improved hierarchical clustering algorithm simplifies the data in the data preprocessing process, and divides the points with the same gray value in the first place. In the same cluster, the maximum number of initial clusters is only 256. It can reduce the difficulty of X-ray observation and even find out foreign bodies, thereby assisting doctors in diagnosis.

The present invented method includes A, receiving user sent out print preview beginning instruction, reading said instruction corresponded data set from data source, determining said data set total data quantity, according to definite total data quantity calculating and saving printing said data set page distribution information, B, receiving user sent out print preview request, according to said stored distribution information obtaining request from data source and saving said request corresponded data set content, through preview page displaying stored said request correspondent data set content. The present invention can reduce requirement to memory space, realize print preview according to user requirement in local area only stored data set partial content.

The invention discloses a method for diagnosing early Alzheimer's disease based on artificial intelligence. After acquiring text reading aloud recordings, it is automatically translated into text through an ASR program; and then the text is processed according to the following new algorithm of NLP to determine whether the user has AD. Compared with the traditional NLP algorithm, the new algorithm obtains the feature sets of the AD group and the healthy person group respectively, and performs set operations on the feature sets to achieve effective dimensionality reduction of the features, which not only improves the recognition accuracy of the model, but also reduces the accuracy of the algorithm. The demand for memory space speeds up the calculation speed. This method can be applied to computer terminals as well as mobile terminals. The user only needs to speak for a few minutes according to the prompts, without the intervention and analysis of professional doctors. The machine can give the judgment of whether the user suffers from AD through artificial intelligence. The method does not cause trauma to the human body, has low cost, fast diagnosis speed, and is easy to use. It is an effective technical means for large-scale screening of early AD.