Efficient verification of recognition results

• US 7,039,256 B2
• Filed: 07/03/2002
• Issued: 05/02/2006
• Est. Priority Date: 07/12/2001
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Zlotnick, Aviad, Shukevich, Svetlana
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US10/191,035
• Publication Number:
  US 20030012460A1
• Time in Patent Office: 1,399 Days
• Field of Search: 345/157, 345/161, 345/163, 345/167, 345/173, 345/179, 345/180, 345/764, 345/773, 345/780, 345/11, 345/33, 382/119, 382/177, 382/187, 382/188, 382/189, 382/309, 382/311, 382/313, 382/314, 382/315, 382/317, 382/321, 382/225, 382/228, 715/505, 715/506, 715/507, 715/509, 715/529, 715/526, 715/754
• US Class Current: 382/311
• CPC Class Codes: G06V 10/987 with the intervention of an operator

Abstract

A method for increasing efficiency of interaction by an operator with data on a computer display includes presenting the data to the operator on the computer display, and providing multiple instances of an on-screen control at different locations on the display for selection by the operator using a pointing device linked to the display. The control is actuated responsive to the selection by the operator of any of the instances of the control on the display.

Claims

1. A method for automated injection, comprising:

receiving a collection of input items;

assigning respective classifications to the items in the collection, the classifications of the items having respective confidence attributes associated therewith;

forming a group of the items whose respective classifications are the same, with respective confidence attributes in a first attribute range;

adding to the group a selection of the items for which the confidence attributes associated with the respective classifications are in a second attribute range, such that the classifications whose confidence attributes are in the second attribute range are likelier to be erroneous than those whose confidence attributes are in the first attribute range;

presenting the group of the items together on a computer display; and

receiving an input from an operator indicating the items on the display whose classifications are perceived by the operator to be erroneous,

wherein adding the selection of the items to the group comprises selecting the items to be added such that the classifications of the added items are the same as the classifications of the items in the group whose respective confidence attributes are in the first attribute range, and

wherein assigning the respective classifications comprises assigning first and second classifications to each of at least some of the items, with respective first and second confidence attributes, such that the first confidence attribute is indicative of a higher level of confidence than the second confidence attribute, and wherein selecting the items to be added comprises selecting the items such that the second classification of the added items is the same as the classifications of the items in the group whose respective confidence attributes are in the first attribute range.

2. An apparatus for automated injection of a collection of items, comprising:

a display, arranged to present the items to an operator;

a user interface device, coupled to the display so as to enable the operator to provide an input selecting one or more of the items on the display, wherein the items in the selection added to the group have the same classifications as the classifications of the items in the group whose respective confidence attributes are in the first attribute range; and

a processor, which is arranged to assign respective classifications to the items in the collection, the classifications of the items having respective confidence attributes associated therewith.

wherein the processor is arranged to form a group of the items whose respective classifications are the same, with respective confidence attributes in a first attribute range, and to add to the group a selection of the items for which the confidence levels associated with the respective classifications are in a second attribute range, such that the classifications whose confidence attributes are in the second attribute range are likelier to be erroneous than those whose confidence attributes are in the first attribute range, and to drive the display to present the group of the items together so as to receive the input from the operator to indicate the items whose classifications are perceived by the operator to be erroneous,

and wherein the processor is further arranged to assign first and second classifications to each of at least some of the items, with respective first and second confidence attributes, such that the first confidence attribute is indicative of a higher level of confidence than the second confidence attribute, and wherein the items in the selection added to the group are such that the second classification of the hems in the selection is the same as the classifications of the items in the group whose respective confidence attributes are in the first attribute range.

3. A computer software product for automated injection of a collection of items, the product comprising a computer-readable medium in which program instructions are scored, which instructions, when read by a computer, cause the computer to drive a display so as to present the items to an operator, and to receive an input made by the operator selecting one or more of the items on the display, wherein the items in the selection added to the grow, have the same classifications as the classifications of the items in the group whose respective confidence attributes are in the first attribute range;

the instructions further causing the computer to assign respective classifications to the items in the collection, the classifications of the items having respective confidence attributes associated therewith, and to form a group of the items whose respective classifications are the same, with respective confidence in a first attribute range, and to add to the group a selection of the items for which the confidence levels associated with the respective classifications are in a second attribute range, such that the classifications whose confidence attributes are in the second attribute range are likelier to be erroneous than those whose confidence attributes are in the first attribute range; and

the instructions further causing the computer to drive the display to present the group of the items together so as to receive the input from the operator to indicate the items whose classifications are perceived by the operator to be erroneous.

wherein the instructions cause the computer to assign first and second classifications to each of at least some of the items, with respective first and second confidence attributes, such that the first confidence attribute is indicative of a higher level of confidence than the second confidence attribute, and wherein the items in the selection added to the group are such that the second classification of the items in die selection is the same as the classifications of the items in the group whose respective confidence attributes are in the first attribute range.