2001 results about "Retina" patented technology

The present application discloses a low-light image enhancement method based on wavelet transform and Retinex-Net, and belongs to the field of image enhancement technology. In order to solve the problems of colour distortion and lack of details such as edges and textures when Retinex-Net processes some images, the present application adds the wavelet transform, fuses the high-frequency components with regional characteristics, and processes only the low-frequency component with Retinex-Net, to retain more details of edges and textures in the image, and transfers the low-frequency and high-frequency components from the HSV space to the value space for value fusion and stretching, to effectively improve the colour distortion of the image, and also improve the expression of details of the image. The present application retains more detail information while avoiding colour distortion, and the enhancement effect is satisfactory.

A computer-implemented method for operating an artificial intelligence voice agent system includes receiving voice input through communication channels; analyzing converted text through natural language processing (NLP) pipelines implementing intent recognition and sentiment analysis detecting emotional cues using a multimodal large language model (LLM); generating response content using machine learning models trained on domain-specific corpora; converting generated responses to synthetic speech through text-to-speech (TTS) engines; integrating with a customer relationship management (CRM) platforms or an enterprise resource planning (ERP) database; and implementing continuous learning by updating language understanding models using conversation logs, voice recognition parameters based on user feedback, and response generation patterns. One implementation is a computer-implemented system and method that operates a suite of intelligent interactive devices and platforms including an artificial intelligence voice agent, enhanced communication platforms, an intimacy companion system, and augmented / virtual reality eyeglasses. Further, one implementation includes AR / VR eyeglasses that project visual content onto interchangeable lenses or directly onto the user's retina via laser-based retinal projection, provide prescription adjustments, incorporate ear-mounted sensors for monitoring physiological parameters like heart rate, oxygen saturation, and blood pressure, and utilize wireless data transmission, onboard environmental sensing, and remote calibration, all designed to offer dynamically adaptive, secure, and context-aware interactions across communication, personal assistance, health monitoring, and immersive augmented or virtual reality environments.

The present application provides a method for diagnosing and / or evaluating the presence or absence, severity or degree of the improvement of a retinal disease in a subject, which comprises determining and / or evaluating circulatory parameters, retinal function, retina morphology and / or visual relating quality of life (QOL).

A computer-implemented system and method for pupil-directed retinal projection in near-eye displays are disclosed. The computer-implemented system provides smart glasses with directed physical pixels that project light beams / signals directly onto a user's retina based on pupil position and size. The glasses comprise a frame, lenses with directed pixel layers, and sensors for tracking pupil movement. Each directed pixel may generate multiple virtual pixels by rapidly changing its emission angle. The glasses function as prescription lenses, virtual reality displays, and augmented reality devices without traditional optical systems. Additional features include depth sensors, cameras, and connectivity to peripheral devices. The glasses enable a seamless blend of virtual and real-world experiences, creating an immersive “Mixverse” environment. Various input methods, including gesture recognition and brain-computer interfaces, allow for intuitive control and interaction.

The invention discloses a visual time sequence feature network implementation method based on multi-module feature fusion. The system comprises a visual time sequence feature encoder VTFE, a multi-scale self-attention fusion module MSAF, an efficient feature reconstruction engine EFRE and an adaptive feature refinement processor AFRP. The VTFE module fuses a convolutional neural network and an extended long-short-term memory network, and realizes high-precision capture of spatial-temporal features. The MSAF module processes characteristic frequency domain information through fast Fourier transform, and the recognition capability of complex boundaries and noise is enhanced. The EFRE module optimizes feature reconstruction through depth separable convolution and jump connection to maintain global consistency. The AFRP module integrates multi-level features and improves the detail expression ability through deep convolution and an attention mechanism. The method is excellent in performance on a large-scale OCT data set, the segmentation precision of the retina edema and the recognition capability of a fine structure are remarkably improved, and an efficient and non-invasive auxiliary tool is provided for early diagnosis of ophthalmic diseases.

There are provided a method for designing a spectacle lens and a related technique thereof, the method including: a modeling step of dividing a pattern into multiple models with a deviation from a normally worn state of the spectacle lens as decentering, in which a reference model, a decenter model, and a tilt model are prepared as the multiple model; a sensitivity calculation step of calculating a decenter sensitivity and a tilt sensitivity; and a design step of using a base curve value in the vicinity of a balance solution as a base curve of the spectacle lens, wherein a base curve value c [unit: diopter (D)] which is a curvature of a surface in a region H where the on-retinal non-convergence region is not provided on an object-side surface is taken as x-axis, and the decenter sensitivity and the tilt sensitivity [unit: diopter (D)] are taken as y-axis, and an intersection of a plot of the decenter sensitivity and a plot of the tilt sensitivity is taken as the balance solution.

The invention relates to the technical field of image processing, in particular to a super-resolution reconstruction system and method based on a pulse neural network, and the system comprises an image pulse encoder, a pulse feature enhancer and a differentiable pulse decoder. An image pulse encoder simulates a receptive field of a retina by using DoG response, performs adaptive pulse distribution on an input low-resolution image in combination with an image gradient, and converts the low-resolution image into a space-time pulse sequence reflecting a high-frequency region and a low-frequency region in the low-resolution image; a pulse feature intensifier performs coarse-grained and fine-grained structure reconstruction of a low-resolution image on the space-time pulse sequence by using a pulse time sequence dependent plasticity mechanism to obtain a granularity feature pulse; and the differentiable pulse decoder converts the granularity characteristic pulse to obtain a corresponding high-resolution image. According to the method, efficient and low-consumption image super-resolution reconstruction is realized through a bionic retina coding mechanism and a pulse time sequence optimization strategy.

The invention belongs to the field of image data processing, and relates to a diabetic retinopathy image classification system and method based on deep learning, the system is obtained by improving a VMama network model, and a VSS module of the VMama network model is replaced by a VSS-SL module; the VSS-SL module is of a multi-branch structure and comprises a VSS module, an SE attention module and a Local local attention module, one path of input data is input into the VSS module, the other path of input data is input into the Local local attention module and the SE attention module in sequence, the VSS module comprises a first branch path and a second branch path which are parallel, and the second branch path is connected with the first branch path. The features output by the second branch path after standardization of the LN normalization layer are fused with the features output by the first branch path and the features output by the SE attention module; the fused features are input into a linear layer, and the features output by the linear layer and the original input data are subjected to feature addition and then output. The system can classify the diabetic retinopathy pictures at a higher speed, and has a higher accuracy rate.

The invention belongs to the technical field of fundus imaging, and discloses an ultra-wide-angle ellipsoid confocal laser scanning fundus imaging system, which comprises a light splitting module, a light condensing module, a scanning module, a transmitting mirror group, an ellipsoid reflector and a detection module, wherein the center of the scanning module and the center of the transmitting mirror group are located on the same optical axis A, the pupil of the human eye is located at the first focus of the ellipsoidal reflector, and the entrance pupil of the transmitting mirror group is located at the second focus of the ellipsoidal reflector; and the transmitting lens group comprises a movable focusing lens and is used for changing the position of a first image surface of light reflected by the retina of the human eyes when moving along the optical axis A so as to realize clear imaging of the retina of the human eyes with different diopters. Under the condition that a free-form surface is not introduced, ultra-wide-angle multi-wavelength confocal laser scanning fundus imaging with the single intraocular field angle of 200 degrees is achieved, and the full-field optical resolution reaches 15 micrometers. And by moving the focusing lens, imaging compensation can be carried out on human eyes with diopters of-15D to + 15D.

The invention discloses a heterogeneous double-flow fusion method and system for diabetic retinopathy grading. The method comprises the following steps: obtaining an output result of diabetic retinopathy grading by utilizing a heterogeneous double-flow architecture; processing an input fundus image into images with different resolutions; extracting global context features from the low-resolution image by using a lightweight visual Transform model distilled by composite knowledge, and extracting local focus features from the high-resolution image by using a convolutional neural network model; performing interactive fusion on the global context features and the local focus features of the double-branch architecture through a symmetric bidirectional cross attention fusion module to obtain enhanced fusion feature representation; and finally, inputting the fusion features into a classifier, and outputting a severity grading result of the lesion. The method aims at improving the accuracy and robustness of hierarchical diagnosis through deep analysis of global information and local details, and can be applied to the medical fields of clinical computer-aided diagnosis, eye image analysis and the like.

A method of providing a refractive prescription includes: receiving a plurality of images from a sensor, the plurality of images captured sequentially using light from an eye of a living being: determining respective values of an image quality metric (IQM) for respective images of the captured plurality of images: selecting a subset of the plurality of images based on the values of the IQM; and determining and outputting to a user a refractive prescription for the eye based on the subset of the plurality of images. Example embodiments can be employed to produce and output better refractive prescriptions by taking into account dynamics of a patient's eye.

The invention provides a subjective optometry prediction method combining wavefront aberration and optical signals. According to the method, eyeball wavefront aberration data are measured through a wavefront sensor, cornea, crystal and retina biological parameters are obtained by combining multi-view-field scanning of a galvanometer system, and after high-credibility data points are screened, a gradient refractive index eyeball three-dimensional model is constructed by adopting an NURBS algorithm; using finite element analysis to optimize cornea stress distribution, iteratively correcting the model through a deformation energy function, and dynamically compensating eyeball motion errors based on eye movement tracking data; and generating a multi-field-angle visual chart image through ray tracing simulation, and predicting a subjective optometry result in combination with an image quality evaluation algorithm. According to the method, high-precision modeling, dynamic error suppression and intelligent simulation technologies are fused, the optometry prediction accuracy, the personalized adaptation degree and the dynamic scene adaptability are remarkably improved, and an efficient and reliable solution is provided for refraction correction.

The invention relates to the technical field of medical image processing and artificial intelligence, and discloses an artificial intelligence-based retinochoroid disease course structure change monitoring system, which comprises an image acquisition unit, a feature extraction unit, a lesion segmentation unit and the like. The image acquisition unit acquires retina optical coherence tomography sequence image data and fundus color image data; the feature extraction unit extracts a retina choroidal structure feature tensor through a three-dimensional convolutional neural network; the lesion segmentation unit outputs a lesion area probability distribution diagram by using a U-Net segmentation network; the time sequence alignment unit is used for registering the multi-time-point images to generate a displacement change matrix; the dynamic analysis unit extracts related indexes; an abnormal scoring unit constructs a disease course progress score; the decision grading unit outputs disease course stage classification labels; the multi-modal fusion unit fuses the multi-modal features; the report generation unit generates a structured disease course monitoring report. And favorable support is provided for diagnosis and treatment of ophthalmic diseases and illness state tracking.

The invention discloses a diabetes retina image classification method and system based on deep learning, and relates to the technical field of image classification, and the specific steps are as follows: collecting and preprocessing a retina image data set, and constructing a training data set; constructing an initial image classification model based on a deep neural network, and performing iterative training on the initial image classification model by using the training data set to obtain an image classification model; the initial image classification model takes a pre-trained OfficientNet network as a backbone network, and integrates a feature pyramid network structure, a lesion attention module and a classification module; and obtaining a to-be-classified image, preprocessing the to-be-classified image, inputting the preprocessed to-be-classified image into the image classification model, and outputting a classification result. According to the method, the dependence of the model on a specific data source is reduced by using a data enhancement strategy, the diagnostic performance and stability of the model on unseen retina images are improved, and the universality of clinical application is enhanced.

The present disclosure relates to diagnosis of ocular diseases by leveraging an attention-based multimodal graphical neural network (AM-GNN) based on multimodal data that includes one or more image-text pairs. Each image of the image-text pair may depict a retinal scan of a subject that may correspond to one or more imaging modalities. A multimodal dataset may be collected from different imaging modalities by data crawling to automatically collect relevant data for the targeted diseases from identified sources. In some aspects, a concept bank, comprising concepts or terminologies associated with the targeted diseases, may be provided to the AM-GNN to generate a multimodal graph. The AM-GNN may be configured to find an association between a set of nodes including image-text pairs, a set of diseases, and the concepts using an attention mechanism. Based on the multimodal graph, an output may be generated, including a predicted disease and related concept(s).

The invention relates to the technical field of optical elements, and discloses a fog display point diffusion optical system and a preparation method thereof, and the preparation method comprises the steps: obtaining user visual parameters, and building a visual behavior probability density model through kernel density estimation; designing the front surface of the lens based on the model, and generating an asymmetric defocus system coupled with a gazing habit; the rear surface of the lens is designed, and the distribution density of a fog display point diffusion unit is cooperatively modulated by the front surface defocusing amount, the fixation probability and the pupil diameter; and finally integrating front and rear surface design to form an optical lens body. According to the method, the asymmetric defocus field on the front surface and the fog display point diffusion field on the rear surface are subjected to collaborative design, and the defocus intensity and the contrast modulation intensity are accurately applied to the effective retina area of the user through the visual behavior probability density model; the technical problem that a traditional out-of-focus lens is fixed in signal and cannot adapt to individual staring habits and physiological parameter changes is solved.

The invention provides a diabetic retinopathy grading method based on a vision-language pre-training model and a ranking perception prompt strategy. According to the method, an eye ground color image and a corresponding DR grading label are converted into image features and text embedding through an image and text dual-coding mode, matching is carried out through the similarity between the image and the text, and accurate DR grading is achieved. In order to solve the problems of class imbalance and natural sequence modeling, a ranking perception prompt module and a similarity matrix smoothing module are introduced, ranking perception prompt ensures that the model can learn and maintain the sequence relation between different DR levels, and an SMS module effectively relieves the influence caused by data imbalance. The method disclosed by the invention can show relatively high accuracy and robustness in various DR grading tasks, especially under the condition of few samples or unbalanced categories. The method not only improves the grading accuracy, but also provides an effective auxiliary tool for clinical diagnosis, and has a wide application prospect.

A phantom eye includes a curved reflectance standard having a light-receiving surface configured to be illuminated by light and one or more ocular media components positioned such that the light passes through the one or more ocular media components prior to illuminating the light-receiving surface of the curved reflectance standard. The curved reflectance standard mimics an optical property of a retina of a biological eye. The one or more ocular media components mimic an optical property of the biological eye.

Optical lens intended to be worn by a wearer An optical lens intended to be worn by a wearer comprising: —a refraction area having a refractive power based on a prescription for said eye of the wearer; —a plurality of optical elements having a transparent optical function of not focusing an image on the retina of the eye of the wearer when the optical lens is worn in standard wearing conditions, —a zone of interest comprising a subset of the optical elements, each optical elements in the subset bearing a cylinder component on its surface, wherein the zone of interest is of at least 50 mm2, and the standard deviation of the orientations of the cylinder axis of each optical element comprised in the zone of interest is smaller than or equal to 15° with respect to a common predefined direction.

A method for designing a spectacle lens and a related technique thereof, including: a modeling step of dividing a pattern into multiple models with a deviation from a normally worn state of the spectacle lens as decentering, wherein a reference model, decenter model, and tilt model are prepared as the multiple model; a sensitivity calculation step of calculating a decenter and a tilt sensitivity; and a design step of using a base curve value in the vicinity of a balance solution as a base curve of the spectacle lens, wherein a base curve value which is a curvature of a surface in a region where the on-retinal non-convergence region is not provided on an object-side surface is taken as x-axis, and the decenter and tilt sensitivities are taken as y-axis, and an intersection of a plot of the decenter sensitivity and the tilt sensitivity is taken as the balance solution.

The invention relates to the technical field of computer vision, and discloses a robot image recognition system based on a convolutional neural network, and the system comprises a dynamic retina blur sensing module which is used for estimating a pixel-level dynamic blur kernel parameter from an input blur image; the differentiable physical deblurring layer is used for performing feature reconstruction on the blurred image based on the dynamic blurring kernel parameters to generate deblurred image features; and the fuzzy robust CNN backbone network dynamically adjusts the voidage of a convolutional layer according to the dynamic fuzzy kernel parameters so as to adapt to the local fuzzy intensity. The problem of parameter distortion of a data-driven model is solved through an optical flow constraint fuzzy perception module, dilated convolution is dynamically adjusted based on fuzzy intensity to expand a high fuzzy region receptive field, an end-to-end joint training framework is constructed to realize classification error reverse optimization fuzzy kernel parameters, and a two-stage curriculum learning strategy is combined to improve the robustness of the system. The physical model is solidified first and then global optimization is carried out, and the bottleneck of traditional staged training is broken through.

An object displaying system includes a right light signal generator, a left light signal generator, a right combiner, and a left combiner. The right light signal generator generates right light signals for an object. The right combiner receives and redirects the right light signals towards one retina of a viewer to display multiple right pixels of the object. The left light signal generator generates leftght signals for the object. The left combiner receives and redirects the left light signals towards the other retina of the viewer to display multiple left pixels of the object. A first redirected right light signal and a corresponding first redirected left light signal are perceived by the viewer to display a first virtual binocular pixel of the object with a first depth that is related to a first angle between the first redirected right light signal and the corresponding first redirected left light signal.

The invention discloses a display method and equipment. The display method comprises the following steps: acquiring pixel matrix data of a first color component of an original display picture in a target color space; performing fuzzy processing on color components of at least part of pixels in the pixel matrix data of the first color component to obtain a first fuzzy component; and generating and displaying a target display picture based on the first fuzzy component. Through the implementation scheme, fuzzy processing is carried out on part of color components in the display picture, and the effect that the focus moves forwards in the eye axis direction after the part of color components are focused in the human eyes is simulated, so that myopia defocus signals are generated on the retina, myopia formation and development are slowed down, and the eye protection effect is achieved. Meanwhile, part of color components are blurred, the color proportion cannot be obviously reduced, the influence on the picture hue can be reduced, and the user experience is better.

A lens element for a spectacle lens, a contact lens or an intraocular lens, intended to be worn by a wearer having a refraction area having a refractive power based on a prescription for said eye of the wearer and a plurality of n optical elements, at least one of the n optical elements having an optical function of not focusing an image on the retina of the eye of the wearer, the kth optical element being located in a domain defined by a closed contour, k being a positive integer equal or greater than 2 and smaller or equal to n, a coating layer may be deposited on the lens element, wherein, without taking the potential coating layer into account, the least one kth optical element presents as a standard deviation of sphere values of at least 0.4 dpt, where is defined as, H(xi, yi) mean optical curvature operator at position xi, yi of the kth optical element in its domain, being the mean of the mean optical curvatures over the whole domain of the kth optical element, being an integer of number all positions xi yi in the domain of the k-th optical element and being greater than 100.

The invention provides a diabetic retinopathy image recognition method based on federated learning and differential privacy, and belongs to the field of federated learning. The method comprises the following steps: carrying out preprocessing and Poisson sampling on a diabetic retinopathy image data set to initialize a global model located in a central server; the local client obtains parameters of the global model from the central server and constructs a local model; the local client performs training and differential privacy processing on a local model by using local data; the central server receives the parameters uploaded by the clients for secure aggregation, and updates the global model by using the parameters after secure aggregation; if the number of training iterations does not reach the threshold value specified by the user, a result is transmitted to the local model to continue the training process; and when the number of training iterations reaches a threshold value specified by the user, terminating a further iteration process to obtain a trained model. And the problems of gradient leakage and data loss possibly existing in privacy protection by introducing differential privacy in federated learning are balanced.

The invention relates to the technical field of additive manufacturing, and discloses an additive manufacturing lens surface optimization method based on real-time feedback control. The method comprises the following steps: firstly, acquiring eye biometric data and personalized visual demand parameters of a wearer, establishing a personalized optical model of eyeballs according to the eye biometric data and the personalized visual demand parameters, and deducing a retina defocusing amount distribution map; and determining spatial arrangement and geometric morphology parameters of the distributed out-of-focus microstructure layer on the lens according to the atlas. In the additive manufacturing process, the optical material is deposited and solidified layer by layer, and the three-dimensional shape information of the surface of the optical material is obtained in real time after deposition of each layer. And comparing and analyzing the morphology information with a theoretical model to generate a morphology deviation result. And then, a correction instruction of the printing parameters is calculated by using the correction model, and the printing parameters of the additive manufacturing equipment are adjusted in real time, so that real-time compensation and optimization of the morphology deviation are realized, and finally, a high-precision lens product meeting personalized optical design requirements is manufactured.

The invention belongs to the technical field of medical image analysis, and discloses a diabetic retinopathy grading model system using a frequency domain attention mechanism, which comprises a data set construction module, a data preprocessing module, an evaluation index module, a feature extraction module, a frequency domain channel attention module and a frequency domain space attention module. The invention provides a DR grading model based on deep learning, and aims to more accurately identify and classify lesions in fundus images. By introducing a frequency domain channel attention module (FCAM) and a frequency domain space attention module (FSAM), the model can more effectively capture weak lesion features. FCAM improves the sensitivity of a model to a lesion area by fusing frequency domain and channel domain information; according to the FSAM, key pixels are emphasized in a spatial domain and a frequency domain, so that the extraction capability of the model on fine texture features is enhanced.

The invention discloses an OCT (Optical Coherence Tomography) retina image denoising method based on a high-frequency enhanced diffusion model, which is characterized in that a double-branch diffusion model network constructed based on frequency perception Fourier transform attention (FFTA) is used for separating different frequency domains, enhancing specific frequency domain features and fusing the specific frequency domain features into a spatial domain feature map to realize stronger frequency domain perception and processing capability; the invention relates to a time step T coding method for a module of frequency domain attention. The time step T of the diffusion model is used as a parameter to be coded into a frequency domain attention module to participate in self-attention matrix calculation, so that frequency domain feature processing is aligned with the iteration step number of the diffusion model, and different frequency domain information is pointedly processed at different time steps T; the frequency selective hopping mechanism uses pooling operation to obtain a high / low frequency characteristic pattern, so that the network has adaptive frequency domain retention capability for different local parts.

Methods and systems including a first electrode substrate having one or more stimulation electrodes that are configured to apply electrical stimulation signals to a patient's first eye; a plurality of sensor electrodes configured to detect electrical activity from neural cells of the patient during delivery of an electrical-stimulation therapy, wherein the plurality of sensor electrodes includes a first sensor electrode and a second sensor electrode; a first return electrode configured to be placed in a location on the patient such that an electrical current is formed between at least one of the one or more stimulation electrodes and the first return electrode; and a stimulation controller configured to control the electrical current formed between the at least one of the one or more stimulation electrodes and the first return electrode such that the electrical current passes through a retina of the patient's first eye and delivers the electrical-stimulation therapy.

The invention provides an anti-dazzling traffic sign generation system, device and method, and the method enables the image data used for detection to be accurately recognized in a weak light environment through the preprocessing of the environment image data during the operation of a vehicle. Traffic sign recognition and screening and anti-dazzling target recognition and screening are carried out on the image data, and finally a traffic sign icon with a shielding frame is generated; the traffic sign icon with the shielding frame can effectively prevent light rays of a projection light machine from directly irradiating the retina of pedestrians or other drivers, the dazzling feeling is relieved, and more convenient and clearer driving instructions, driving safety of the drivers and visual protection of other road users are provided by optimizing the definition of the projection sign.