Inventors list |
Assignees list |
Classification tree browser |
Top 100 Inventors |
Top 100 Assignees |
Ke Wei
Ke Wei, San Mateo, CA US
| Patent application number | Description | Published |
|---|---|---|
| 20090043853 | EMPLOYING PIXEL DENSITY TO DETECT A SPAM IMAGE - A network device and method are directed towards detecting and blocking image spam within a message by performing statistical analysis on differences in edge pixel distribution patterns. An image spam detection component receives a message with an image attachment. Physical characteristics of the image are examined to determine whether the image is a candidate for further analysis. If so, then the image may be converted to a grayscale image, and then performing edge detection, followed by the elimination of non-maxima and thresholding of weak edges. Edge pixels and then employed to determine a normalized pixel density distribution (PDD). Various statistical analyses are applied to the resulting normalized PDD to determine a likelihood that the image is spam. A signature based exemption may be applied to images improperly identified as spam, based on trusted user feedback. | 02-12-2009 |
| 20110078269 | EMPLOYING PIXEL DENSITY TO DETECT A SPAM IMAGE - A network device and method are directed towards detecting and blocking image spam within a message by performing statistical analysis on differences in edge pixel distribution patterns. An image spam detection component receives a message with an image attachment. Physical characteristics of the image are examined to determine whether the image is a candidate for further analysis. If so, then the image may be converted to a grayscale image, and then performing edge detection, followed by the elimination of non-maxima and thresholding of weak edges. Edge pixels and then employed to determine a normalized pixel density distribution (PDD). Various statistical analyses are applied to the resulting normalized PDD to determine a likelihood that the image is spam. A signature based exemption may be applied to images improperly identified as spam, based on trusted user feedback. | 03-31-2011 |
Ke Wei, San Jose, CA US
| Patent application number | Description | Published |
|---|---|---|
| 20090021778 | Approach for processing print jobs on printing devices - An approach is provided for remotely processing locked print jobs. A printing device discovers other printing devices on a network that store locked print jobs. A user enters user identification data and the printing device displays the locked print jobs stored on the other printing devices that are associated with the user. The user selects a particular locked print job. The printing device requests the particular locked print job from the printing device that stores the locked print job and then processes the locked print job locally. An approach is also provided for a printing device to forward print jobs to other printing devices. The printing device discovers other printing devices on a network and the printing attributes of those printing devices. The printing device determines another printing device that is capable of processing a print job and forwards the print job to the printing device for processing. | 01-22-2009 |
| 20100325716 | Managing Access To A Document-Processing Device Using An Identification Token - A method and apparatus for accessing a document-processing device is provided. A request to access the document-processing device is received by the document-processing device. For example, the request may be a request to configure the document-processing device or a request to produce an electronic copy of a document. The document-processing device reads authentication data from an authentication token, which is a portable physical object associated with the user that issued the request. For example, the authentication token may be a proximity card, a common access card (CAC), a smart card, a credit card, a driver's license, or a cell phone. The document-processing device determines, based on the authentication data, whether the user has sufficient user access privileges to perform the request. If user has sufficient user access privileges to perform of the request, then the document-processing device performs the request. | 12-23-2010 |
Ke Wei, Cupertino, CA US
| Patent application number | Description | Published |
|---|---|---|
| 20090316183 | Performance Of A Locked Print Architecture - Techniques are provided for processing a job, such as a print job or a facsimile (fax) job. A printing device comprises multiple modules that are developed in different programming languages. An inter-process communication channel is established between (a) a first module that is developed in a platform-independent programming language and (b) a second module that is developed in a platform-dependent programming language. The first module receives user input that identifies a particular print job. In response to the user input, the first module sends, via the inter-process communication channel, one or more instructions to the second module, which retrieves the print job, decrypts the print job, and causes the print job to be executed. | 12-24-2009 |
| 20100002249 | Locked Print With Intruder Detection And Management - A printing device includes a user interface, a print module and a locked print module. The locked print module is configured to examine a plurality of print data received by the printing device to determine whether locked printing is specified for any electronic documents contained in the plurality of print data. If locked printing is specified for any of the electronic documents contained in the plurality of print data, then the corresponding print data is stored on the printing device and not processed for printing. The locked print module is further configured to verify password data with respect to user identification data. If the password data is not successfully verified with respect to the user identification data, then the locked print module causes print data that is both stored on the printing device and associated with the user identification data to be deleted from the printing device. | 01-07-2010 |
Ke Wei, Palo Alto, CA US
| Patent application number | Description | Published |
|---|---|---|
| 20090216841 | IDENTIFYING IP ADDRESSES FOR SPAMMERS - Detecting and blocking spam messages using statistical analysis on distributions of message sizes for a given IP address. Mail volumes are examined to model a distribution of volumes to cluster IP addresses. The messages sizes may distributed across ranges of message sizes, which is then used to determine an entropy of message sizes for the given IP address. The entropy of the given IP address may be compared to entropies of known good IP addresses, and if a difference between the entropies is statistically significant, then the given IP address may be determined to be an IP spammer. User feedback may also be employed to further characterize an IP address. For example, a number of messages from the IP address may be sent to intended recipients. User feedback may then be monitored to determine whether to the IP address should be reclassified. | 08-27-2009 |
| 20090220166 | FILTER FOR BLOCKING IMAGE-BASED SPAM - A network device and method are directed towards detecting and blocking image spam within a message by employing a weighted min-hash to perform a near duplicate detection (NDD) of determined features within an image as compared to known spam images. The weighting for the min-hash is determined based on employing a machine learning algorithm, such as a perceptron, to identify an importance of each bit in a signature vector of the image. The signature vector is generated by extracting a shape of text in the image using a Discrete Cosine Transform, extracting low-frequency characteristics using a high-pass filter, and then performing various morphological operations to emphasize the shape of the text and reduce noise. Selected feature bits are extracted from the lowest frequency and intensity bits of the resulting signal to generate the signature vector used in the weighted min-hash NDD. | 09-03-2009 |