摘要:
Methods and systems are provided for sharing a digital image depicting one or more faces. The method may include linking a plurality of computer terminals to a computer network, each computer terminal associated with an individual; receiving a digital image at at least one of the computer terminals; executing a face recognition routine on the digital image, the face recognition routine detecting at least one face in the digital image, each detected face corresponding to a person, the face recognition routine recognizing at least one of the persons as being one of the individuals; and for each individual recognized in the digital image by the face recognition routine, initiating dissemination of the digital image to the computer terminal associated with respective individual whose face is recognized in the digital image.
摘要:
The present invention provides, in at least one aspect, methods and systems that detect at least one face in at least one digital image, determine and store area co-ordinates of a location of the at least one detected face in the at least one digital image, apply at least one transformation to the at least one detected face to create at least one portrait of the at least one detected face, rotate the at least one portrait at least until the at least one portrait is shown in a vertical orientation and a pair of eyes of the at least one face shown in the at least one portrait are positioned on a horizontal plane; and store the rotated at least one portrait.
摘要:
Disclosed is a method for intelligently displaying a sports game video for a multimedia mobile terminal, the method including the steps of: determining if a camera shot existing in the sports game video is a long-shot; when the camera shot is determined as a long-shot, determining a ROI within an image frame of the sports game video; and when the camera shot is determined as a non-long-shot, displaying the image frame on the mobile terminal, and, when the camera shot is determined as a long-shot, enlarging and displaying the ROI on the mobile terminal.
摘要:
A multiple ROI (region of interest) setting method and apparatus in scalable video coding and an ROI reconstructing method and apparatus are provided. The multiple ROI setting apparatus includes: an ROI setting unit which sets at least one or more ROIs and allocates ROI identification numbers to the each of ROIs; a mapping unit which allocates at least one or more slice group identification numbers to the at least one or more ROI identification numbers; and a message generating unit which generates a message including ROI-associated information, slice-group-associated information, mapping information on mapping of the ROI identification number to the at least one or more slice group identification numbers, and scalability information.
摘要:
The present invention relates to modality conversion for supporting Quality of Service (QoS) according to media resources, which includes the steps of receiving a modality conversion descriptor in which the characteristics of the modality conversion of the multimedia contents are described, receiving the multimedia contents, and converting the modality of the multimedia contents into a modality determined according to a media resource and the modality conversion descriptor. According to the present invention, a systematic approach to a design for an overlap content value model is provided so that the conversion boundaries between modalities can be quantitatively calculated. As a result, the correlation between various modalities can be established in a single model, and modality conversion supporting the optimal QoS can be performed.
摘要:
Provided is an improved pornography blocking technique which blocks pornography on the basis of the contents of multimedia data. First, feature descriptor is extracted from multimedia data inputted from the Internet by using MPEG-7 scheme. And referring to reference pornography database which stores reference pornography in the form of feature descriptor, the similarity degree between the extracted feature descriptor and the feature descriptor of the reference pornography is measured by calculating the vector distance between the two feature descriptors. And it is determined whether the inputted multimedia data is pornography or not, by comparing the measured similarity degree with the similarity measurement threshold value. According to the invention, accurate pornography determining is possible, because the invention uses the contents of the multimedia data for determining. And rapid and efficient pornography determining is possible, because the invention uses feature descriptor with less information, instead of the original multimedia data.
摘要:
Disclosed are a method and a system that could adaptively improve the visual quality of people with low-vision impairment, regardless of network and terminal. The low-vision impairment is described by a set of “symptoms” that is semantically defined. As the description tool of low vision impairments, it is flexible and reliable to use the proposed “symptoms” based descriptions rather than individually identified names of eye disease, because the user can describe his/her low-vision impairment by specifying associated symptoms based on his/her own experience. The inputted visual contents are adaptively transformed according to the low vision-impairment.
摘要:
The present invention relates to a method and apparatus for clearly detecting color information in front of a vehicle, and an object of the present invention is to accurately and efficiently show color-related traffic information, such as traffic lights and signs, and the whole color information of objects to color-blind people including people with dichromacy or anomalous trichromacy. The present invention provides a method of compensating for the colors of video frame data provided by a front camera, which includes the steps of compensating the video frame data, which is output from the camera, for external environment, such as surrounding colors and brightness, selecting a color range preferred by a user, compensating for the colors of the color-compensated video frame data according to the user's color blindness degree that was input or will be input, and transmitting external scenes, such as the front scene of the vehicle, to the user using a user interface considering user preference.
摘要:
A texture description method in frequency domains and a texture-based retrieval method using the same, in which image signals are converted into those in a frequency domain of a Polar coordinate system. The texture description method in the frequency domain includes a first step of generating a frequency layout by partitioning the frequency domain into a set of feature channels; a second step of extracting the texture feature values of the image from the respective feature channels; and a third step of constituting a texture descriptor of the image in a vector form using the texture feature values extracted from the respective feature channels of the frequency layout. In a texture-based retrieval described in the frequency domain, a retrieval method capable of satisfying respective or all the retrieval conditions such as scale-, rotation- and intensity-invariant retrieval of relevant texture images is provided. Also, a retrieval method of computing the rough scheme of texture to provide a browsing functionality in retrieving is provided.
摘要:
The present invention relates to modality conversion for supporting Quality of Service (QoS) according to media resources, which includes the steps of receiving a modality conversion descriptor in which the characteristics of the modality conversion of the multimedia contents are described, receiving the multimedia contents, and converting the modality of the multimedia contents into a modality determined according to a media resource and the modality conversion descriptor. According to the present invention, a systematic approach to a design for an overlap content value model is provided so that the conversion boundaries between modalities can be quantitatively calculated. As a result, the correlation between various modalities can be established in a single model, and modality conversion supporting the optimal QoS can be performed.