The embodiments of the present invention provide an object detection method, a neural network training method, an object detection device, a neural network training device and an electronic apparatus.The object detection method includes the following steps that: a plurality of fused feature patterns are acquired from an image to be processed through a deep convolutional neural network for targetarea frame detection, a plurality of first feature patterns are acquired from a first subnet having at least one down-sampling layer, and a plurality of second feature patterns are acquired from a second subnet having at least one up-sampling layer, the plurality of first feature patterns and the plurality of second feature patterns are fused, so that the fused feature patterns can be obtained; and target area frame data are obtained according to the fused feature patterns. Since the fused feature patterns well characterize semantic features such as layout and front background information andlow-level detail features such as small-sized object information; the target area frame data of large and small objects included in the image can be effectively extracted according to the fused feature patterns; and therefore, the accuracy and robustness of object detection can be improved.

Key point detection method, neural network training method, devices and electronic apparatus

The invention discloses a medical image expression generating system, a training method and an expression generating method thereof After a medical image acquisition unit acquires a two-dimensional medical image, a convolutional neural network unit extracts the image characteristic of the medical image and converts the image characteristic to an image characteristic vector, and then outputs the image characteristic vector to a pre-established first vector space A circulating neural network unit determines a semantic characteristic vector which corresponds with the image characteristic vector according to a correspondence between the image characteristic vector included in the pre-established first vector space and a semantic characteristic vector included in a second vector space, and furthermore performs outputting An expression output unit converts the semantic characteristic vector which matches the image characteristic vector to a corresponding natural language and performs outputting Therefore the expression generating system realizes simple reading and analyzing to the medical image and furthermore has advantages of improving image reading efficiency, improving image reading quality and greatly reducing misdiagnosing probability

Medical image expression generating system, training method and expression generating method thereof

The invention discloses a license plate recognition method based on depth learning, a recognition device, equipment and a storage medium. The license plate recognition method based on depth learning comprises steps: a single detector is adopted to carry out feature extraction on an original photographed image, and a target license plate image is acquired; correction processing is carried out on the target license plate image to obtain a corrected license plate image; and a bi-directional long and short-term memory model is adopted to recognize the corrected license plate image, and target license plate information is acquired. When the license plate recognition method based on depth learning is used for license plate recognition, the recognition efficiency is high, and the accuracy is higher.

License plate recognition method based on depth learning, recognition device, equipment and storage medium

The invention discloses a video background blurring terminal and method, and relates to the technical field of communication. The video background blurring terminal comprises a first determining module and a starting module; the first determining module determines a present video scene according to present time and present position information; and the starting module starts a background blurring mode when the present video scene is a preset background blurring background. The present video scene is determined according to the present time and present position information, a present video object is determined according to a contact list, the background blurring mode can be started automatically according to the video scene or object in video chatting or live-streaming, the user privacy is protected effectively via the background blurring mode, and the user experience in video chatting or live-streaming can be improved.

Video background blurring terminal and method

The invention discloses a video playing jumping method. The video playing jumping method comprises steps that during video file playing, a correlation between the video file and a preset preview-assisted file is established, and the preview-assisted file comprises the frame description information and the frame time information of the video file; when a video playing jumping instruction is received, image scene description information input by a user is acquired; whether the frame description information, which is in accordance with the image scene description information in a way of meeting a preset matching rule, exists in the preview-assisted file is determined; when the frame description information exists in the preview-assisted file, the frame time information corresponding to the matched frame description information is acquired, and the playing jumping of the video file is carried out according to the acquired frame time information. The invention also discloses video playing jumping equipment and a computer readable storage medium. Rapid and accurate jumping of video playing points is realized.

Video playing jumping method, video playing jumping equipment, and computer readable storage medium

The present invention discloses an image identification method and device, belonging to the image processing field. The method comprises: obtaining a target image which an image to be identified; performing feature extraction of the target image through a presetting convolution neural network model, and obtaining the attribute vectors of the target image, wherein the attribute vectors include the probability of a plurality of presetting word attributes in the target image; and performing semantic analysis processing of the attribute vectors trough the presetting convolution neural network model, and obtaining the descriptive statement of the target image, wherein the descriptive statement is configured to describe the content of the target image. Namely, the image identification method and device can combine the image identification and the natural language processing to realize that the target image is converted to the descriptive statement in a character mode so as to vividly describe the concrete content of the target image in more detail and improve the image identification effect.

Image identification method and device

The invention provides a text recognition method and device. The method comprises: determining convolutional neural network (CNN) features of a text image and obtaining an eigenvector sequence of a preset dimension; and using a recurrent neural network (RNN) to decode the eigenvector sequence of the preset dimension, and obtaining texts in the text image to be recognized. According to the technical scheme provided by embodiments of the invention, the method combines the CNN and RNN to achieve integral recognition of the text image to be recognized, so that the method avoids the problem that texts need to be separated character by character and then recognized character by character in the prior art which leads to accumulated errors, and the text recognition rate can be improved.

Text recognition method and device

The invention discloses a target object positioning method and device in pictures. Comprising: scaling the original picture according to the first preset zoom ratio of the trained first full convolution neural network to obtain the first picture; the first picture is input into the first full convolution neural network, the convolution is processed by the first convolutional neural network, and the first thermal map is outputted; determining a candidate region of the target object in the original picture based on the probability value corresponding to each coordinate point on the first heat map; inputting the image content corresponding to the candidate region into the trained second full convolution neural network, and performing the convolution processing by the second full convolution neural network, and outputting the second thermal map; the position of the target object in the original picture is determined based on the value corresponding to each coordinate point on the second heat map. The disclosed technical program of the positioning method and device can greatly reduce the data amount of the processed image and improve the recognition efficiency of the target object.

Target object positioning method and device in pictures

The invention discloses a model training method and device, and belongs to the field of image processing. The method includes selecting a training sample set from a test sample set, training to obtain an identification model according to samples included in the training sample set, the training sample set being a subset of the test sample set, the training sample set including positive samples and negative samples, the number of the negative samples in the training sample set being smaller than that of the negative samples in the test sample set, identifying samples included in the test sample set according to the identification model, and updating the identification model according to samples that are wrongly identified; the problem that since the samples are limited in number, a face identification model obtained by training is not accurate enough is solved; after the identification model is obtained by training a limited number of samples, the identification model is updated again according to the samples that are wrongly identified, the identification model can be constantly optimized, and thus the accuracy is improved when the identification model is used for identification.

Model training method and device

The invention relates to a convolutional neural network training method, an image identification method and an image identification device. The image identification method based on a convolutional neural network comprises the following steps: obtaining a trained convolutional neural network, wherein the trained convolutional neural network is obtained by performing convolutional neural network training on training samples and an initial convolutional neural network, abandoning part of a computing layer in each iterative computation in the training process, and using unit mapping to replace the abandoned computing layer; preprocessing a to-be-identified image to get a test sample; and performing image identification on the test sample according to the trained convolutional neural network to get an identification result. By using the technical scheme, the training time and memory are saved, and the training of more layers of CNN is made into reality. Moreover, more layers of CNN trained are used to perform image identification, and the accuracy of image identification is ensured.

Convolutional neural network training method, image identification method and image identification device

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yang Song

Author Tools

Chat about Author