Apple Inc.

Larry S Yaeger

Giulia Maria Pagallo

Richard Francis Lyon

Richard W Fabrick, Ii

Brandyn Webb

Charles J Migos

Jean-Pierre Mouileseaux

A multimedia editing application includes a plurality of gestures that are used to control transport and playback, timing, editing, view management, and other functions of the application. The gestures have shapes or characteristics that are visually mnemonic of their associated functions or the objects on which the functions operate, but which themselves are not linguistic forms such as letters or numbers which are derived from the names of the associated functions. The visual mnemonics may connote the motion or shape of a part of the human body.

Gesture control of multimedia editing applications

An ink manager running at a computer system receives ink information entered at a pen-based input/display device and accumulates the ink information into ink strokes. The ink manager communicates with a handwriting recognition engine and includes an ink phrase termination engine that is configured to detect the occurrence of one or more ink phrase termination events by examining the ink information. Upon the occurrence of an ink phrase termination event, the ink manager notifies the handwriting recognition engine and organizes the preceding ink strokes into an ink phrase data structure. The ink manager may also pass the ink phrase to an application executing on the computer system that is associated with the ink information, and it, in response, may return a reference pointer and a recognition context to the ink manager. The reference pointer and recognition context are then appended to the ink phrase data structure.

Method and apparatus for acquiring and organizing ink information in pen-aware computer systems

An ink manager running at a computer system receives ink information entered at a pen-based input/display device and accumulates the ink information into ink strokes. The ink manager communicates with a handwriting recognition engine and includes an ink phrase termination engine that is configured to detect the occurrence of one or more ink phrase termination events by examining the ink information. Upon the occurrence of an ink phrase termination event, the ink manager notifies the handwriting recognition engine and organizes the preceding ink strokes into an ink phrase data structure. The ink manager may also pass the ink phrase to an application executing on the computer system that is associated with the ink information, and it, in response, may return a reference pointer and a recognition context to the ink manager. The reference pointer and recognition context are then appended to the ink phrase data structure. Utilizing the recognition context identified by the application, the handwriting recognition engine generates one or more hypotheses for the ink phrase, and provides them to the ink manager. The ink manager forwards the hypotheses together with the reference pointer to the application and may also append them to the ink phrase data structure.

After each complete stroke in a handwriting recognition process, a hypothesis is generated whether a word break is present between the previous stroke and the new stroke. This hypothesis is weighted with a probability of a word-break occurring between the strokes. This probability is determined from the geometrical relationships between characters. Subsequently, a word search is carried out on the basis of these weighted hypotheses, to identity the most likely candidates for the words represented by the written strokes. A user interface is provided that offers the user a limited list of alternative word recognitions for a group of characters. These recognitions undergo segmentation filtering, in accordance with the word breaks of the selected hypotheses, to present the user with only those alternatives having the same groupings of strokes.

Character segmentation technique with integrated word search for

A classification system is provided for combining multiple input representations by a single neural network architecture. In such a classification system having a single neural network architecture, classification channels corresponding to various input representations may be integrated through their own and shared hidden layers of the network to produce highly accurate classification. The classification system is particularly applicable to character classifying applications which use stroke and character image features as the main classification criteria, along with scalar features such as stroke count and aspect ratio features as secondary classification. The classification channels corresponding to the scalar features may be cross wired to the classification channels corresponding to the main input representations for further improving the accuracy of the classification output. Because a single neural network architecture is used, only one, standard training technique is needed for this classification system, special data handling is minimized, and the training time can be reduced, while highly accurate classification is achieved.

Classifying system having a single neural network architecture for

A statistical classifier for pattern recognition, such as a neural network, produces a plurality of output signals corresponding to the probabilities that a given input pattern belongs in respective classes. The classifier is trained in a manner such that low probabilities which pertain to classes of interest are not suppressed too greatly. This is achieved by modifying the amount by which error signals, corresponding to classes which are incorrectly identified, are employed in the training process, relative to error signals corresponding to the correct class. As a result, output probabilities for incorrect classes are not forced to a low value as much as probabilities for correct classes are raised.

Adaptive statistical classifier which provides reliable estimates or

A statistical classifier that can be used for pattern recognition is trained to recognize negative, or improper patterns as well as proper patterns that are positively associated with desired output classes. A set of training samples includes both the negative and positive patterns, and target output values for the negative patterns are set so that no recognized class is indicated. The negative patterns are selected for training with less frequency than the positive patterns, and their effect on training is also modified, so that training is focused more heavily on improper patterns.

Method for training an adaptive statistical classifier with improved

A statistical classifier that can be used for pattern recognition is trained to recognize negative, or improper patterns as well as proper patterns that are positively associated with desired output classes. A set of training samples includes both the negative and positive patterns, and target output values for the negative patterns are set so that no recognized class is indicated. The negative patterns are selected for training with less frequency than the positive patterns, and their effect on training is also modified, so that training is focused more heavily on positive patterns.

Method for training an adaptive statistical classifier to discriminate

A method and apparatus for determining and displaying or preventing a collision between two objects. Certain characteristics of these two objects such as their sizes, orientations, and velocities, are inputted. Based upon these characteristics, a collision contour is generated about the first object. If either or both object(s) had been moved, the collision contour is generated based on a velocity outline to account for the velocity effects. These two objects have collided if the second object's centerpoint is included in the collision contour. Otherwise, the two objects have not collided. The result is then portrayed on a graphics display device.

Growing community of inventors

Los Gatos, CA, United States of America

Larry S Yaeger