In our previous report we briefly discussed the types of reverse image search tool available on the Internet. We also introduced the concept of reverse image searching and its importance to businesses. This report summarises a hands-on experience of using a reverse image search tool.
Using reverse image search engines for prior art searches
The following screenshots of Google Images provide an overview of the reverse image search process (please note that the example is exemplary in nature and has no association to any organisation or project).
Figure 1. Drag and drop an image on Google Images
Figure 2. Results retrieved through Google Image search
Figure 3. Sample US Patent 5,040,485
This example shows how helpful reverse image search engines can be when searching for patents using images. It will be evident to professional searchers that reverse image search engines can be helpful in prior art searches – especially freedom-to-operate, validity and invalidity searches – which use a reference image or patent document for searching similar technologies. While the above example successfully identifies the patent from its image using a reverse image search engine, there is still scope for improvement in these engines vis-à-vis searching patent literature using (for example) product images, hand sketches and cycle diagrams.
Nowadays, a great deal of emphasis is being placed on automation – ‘bots’ are minimising human involvement in hundreds of sectors. With the help of electronic design automation tools and keyword-based analytics, the field of patent searching and analytics is advancing at a rapid pace. However, searching for prior art using images is still a relatively untouched domain. Despite a multitude of tools that host reverse image search engines, their application is still limited. Further, the documents retrieved through reverse image searches are generally not as relevant as those retrieved through concept-based searches. Thus, there is huge scope for maturing this technology and applying it to the domain of professional patent searching. Needless to say, when it comes to prior art searches, the use of human analytics can never be done away with.
This article first appeared in IAM. For further information please visit www.IAM-media.com.