Xcavator from CogniSign – Semi-manual search based on recording the color at key points chosen by the user. Seems like a good idea, why doesn’t it work? Experiment: an image of rose with 20 key points returns an image of a girl in a red bikini.

Pixcavator 1.23 (328K). For your convenience, the option of shrinking the image prior to processing has been added. Two bugs have been fixed.

Pixcavator 1.2 (324K). Changes in the new version:

• The interface has been reworked. Windows and buttons are rearranged, so that the images can be larger.
• Graphics has been changed.
• A new simplification parameter has been added - compactness or roundness. It is computed as (perimeter squared)/(4*PI*area). As before if the compactness of an objects is less than this setting, the object is removed from the image. There is also an unused setting. Conceivably, the user can introduce something of his own.
• The memory leakage problem has been solved.
• There is still a bug.

Face search and identification in photo albums. Experiment: it may return a sneaker. This venue since has been abandoned for “likeness” search for online shopping, like.com. What a joke! Available only within just a few very narrow categories, shoes, watches, etc. Whether it actually uses image analysis is unclear. Experiment: an image of an analogue watch returns an image of a digital watch.