Abstract: A method for processing breast tomosynthesis images includes: obtaining multiple breast images, performing binarization operation and pooling operation to at least one marked breast image to obtain a lesion mask; training a convolutional neural network (CNN) according to the breast images and the lesion mask; obtaining multiple cropped images from the breast images of different layers according to a particular two-dimensional position, and inputting each cropped image into the CNN to obtain cropped heat maps; inputting the cropped heat maps into a recurrent neural network (RNN) in an order of the levels to obtain output heat maps, and combining the output heat maps to obtain a integrated heat map, and training the RNN according to the integrated heat map and the lesion mask.

Abstract: A method for processing breast tomosynthesis images includes: obtaining multiple breast images, performing binarization operation and pooling operation to at least one marked breast image to obtain a lesion mask; training a convolutional neural network (CNN) according to the breast images and the lesion mask; obtaining multiple cropped images from the breast images of different layers according to a particular two-dimensional position, and inputting each cropped image into the CNN to obtain cropped heat maps; inputting the cropped heat maps into a recurrent neural network (RNN) in an order of the levels to obtain output heat maps, and combining the output heat maps to obtain a integrated heat map, and training the RNN according to the integrated heat map and the lesion mask.

Abstract: A recognition system includes an image capturing device and a server. The image capturing device generates a Mth-layer calculation result based on image data and a convolutional neural network (CNN), and transmits feature information associated with the Mth-layer calculation result. M is a positive integer, M is equal to or greater than 1, M is less than or equal to N, and N is a predetermined positive integer. The server receives the feature information. The server generates a Kth-layer calculation result based on the feature information and the CNN by an iterative method when M is less than N. K is a positive integer which is greater than M and less than or equal to N. The server generates a first recognition result associated with the image data based on the Kth-layer calculation result and a first recognition model when K is equal to N.

Abstract: A recognition system includes an image capturing device and a server. The image capturing device generates a Mth-layer calculation result based on image data and a convolutional neural network (CNN), and transmits feature information associated with the Mth-layer calculation result. M is a positive integer, M is equal to or greater than 1, M is less than or equal to N, and N is a predetermined positive integer. The server receives the feature information. The server generates a Kth-layer calculation result based on the feature information and the CNN by an iterative method when M is less than N. K is a positive integer which is greater than M and less than or equal to N. The server generates a first recognition result associated with the image data based on the Kth-layer calculation result and a first recognition model when K is equal to N.

Abstract: An audio fingerprint recognition apparatus, an audio fingerprint recognition method and a non-transitory computer readable medium thereof are provided. The audio fingerprint recognition apparatus stores an under-recognition audio fingerprint datum and an audio fingerprint database having a plurality of audio fingerprint data. Each audio fingerprint datum and the under-recognition audio fingerprint datum is formed of sub-fingerprint bits in a plurality of frequency bands.

Abstract: A distributed multimedia recognition system comprises a user equipment and a server platform, wherein the user equipment is connected to the server platform. The user equipment transmits a recognition request, and performs characteristic extraction on a multimedia, so as to obtain characteristic data. The server platform receives the recognition request, selects one or multiple batches of corresponding reference characteristic data among multiple batches of reference characteristic data recorded in a characteristic database thereof according to a condition of the recognition request, and sends the one or multiple batches of the corresponding reference characteristic data to the user equipment. The user equipment compares the characteristic data to the one or multiple batches of the corresponding reference characteristic data to obtain a recognition result.

Abstract: A computer system is configured for performing audio matching. The computer system includes a client terminal and a server. The client terminal includes a classifier, a first landmark extraction module, a first encoder module and an integration module. The classifier is configured for estimating an identification difficulty. The first landmark extraction module is configured for determining the number of times for landmark extraction, and for extracting first landmarks. The first encoder module is configured for encoding the first landmarks. The server includes a second landmark extraction module, a second encoder module, a hash table, a table-lookup module, an analysis module and a decision module. The second landmark extraction module is configured for extracting second landmarks. The second encoder module is configured for encoding the second landmarks. The table-lookup module is configured for performing a table lookup. The decision module is configured for determining an audio matching result.

Abstract: A computer system is configured for performing audio matching. The computer system includes a client terminal and a server. The client terminal includes a classifier, a first landmark extraction module, a first encoder module and an integration module. The classifier is configured for estimating an identification difficulty. The first landmark extraction module is configured for determining the number of times for landmark extraction, and for extracting first landmarks. The first encoder module is configured for encoding the first landmarks. The server includes a second landmark extraction module, a second encoder module, a hash table, a table-lookup module, an analysis module and a decision module. The second landmark extraction module is configured for extracting second landmarks. The second encoder module is configured for encoding the second landmarks. The table-lookup module is configured for performing a table lookup. The decision module is configured for determining an audio matching result.

Abstract: The present invention relates to an artificial leather and method for making the same. The artificial leather includes a polyester fiber substrate and a thermoplastic polyester elastomer (TPEE) resin layer. The polyester fiber substrate has a plurality of polyester fibers. The thermoplastic polyester elastomer (TPEE) resin layer is disposed adjacent to the polyester fiber substrate, and the material thereof is thermoplastic polyester elastomer (TPEE). Whereby, the material of the all layers of the artificial leather is polyester types, therefore, the whole artificial leather can be melted to recycle and reuse when disposing the artificial leather, so as to achieve the effect of environmental protection.

Abstract: A manufacturing method of electronic packaging includes the steps of preparing a metallic plate having an array of cover portions, soldering the metallic plate to a circuit board having encapsulated areas corresponding to the cover portions and employing a cutting process to obtain multiple electronic packages.

Abstract: An IPTV interactive system and device and an interactive method thereof are provided. The system includes a user side and a server side. The user side has a digital signal control device and includes: a user side time calibration unit; a display unit, used for playing multimedia information; an operation unit, used for outputting a control signal; and a signal receiving unit, used for receiving the control signal. The server side includes: a server side time calibration unit, used for adjusting a time of the user side to be synchronous with the server side; an application server, used for generating and displaying a widget menu page including multiple operation options; a network server, used for transferring an option of the widget menu page corresponding to the control signal to the user side; and a database, used for storing at least a piece of correlation information corresponding to the multimedia information.

Abstract: A method of making a silicon-based miniaturized microphone by means of the application of a combination of processes including a semiconductor manufacturing process and a silicon micro-machining technology. A silicon-based miniaturized microphone made by means of this method has a silicon substrate, which defines a resonance cavity, a diaphragm, a backplate having sound holes, and solder pads. This method is easy to perform, and suitable for a mass production to reduce the manufacturing cost.