Image search accounts for the second most popular form of search queries after web search. According to Bing, these queries make more that 1...
Image search accounts for the second most popular form of search queries after web search. According to Bing, these queries make more that 10 % of total search queries, and as much as 40% of search results include some kind of a visual component. Capitalizing on that fact, Bing has made significant advancements which make it your go-to place when looking for images. Google might be king of web search, but it's image search is no match for Bing's.
Bing has been able to grow its number of image searches by 520% since it started by employing a number of new approaches such as natural language processing, entity understanding, and machine learning etc. On Bing's webmaster blog, it says;
By leveraging the big data generated from billions of searches and information contained within images alongside petabytes of signals from social networks and billions of clicks, we have designed massive machine learning systems that attempt to determine the intent of your image search. With the focus on natural language and entity understanding, for instance, we have improved Bing’s ability to understand people’s intent beyond just queries and keywords.
Understanding generated from Petabytes of data. Let that sink in.
Here are some ways Bing Image Search is better than Google's.
1. Entity Understanding
Is it a person, place or thing? Bing can now understand the focal object someone is looking for. So searching for a person's name would probably turn up results where the subject is in focus - alone. If I search for Obama, I just want to see pictures of him, and not him with the first lady or any other senator/congressman. If I wanted such images, I would have mentioned that in the query. Hence, unlike Google, Bing Image search seems more relevant and to the point.
2. Big Data
It seems that all major tech companies can talk about these days is Big Data. Perhaps rightfully so. Customer feedback is an extremely useful signal. When you click on images you like, Bing stores that data and uses it to interpret future searches and finds results more relevant to you. In this way, Bing is able to do a much better job than Google at predicting exactly what sort of images a user is looking for
3. Computer Vision
Computer vision has to do with understanding how the human brain interprets and processes images. Bing uses computer vision technologies such as deep learning to interpret high dimensional data from the real world to understand the image better.
For example, a search for the tallest peaks in the world is better understood by Bing which processes the image data and integrates a wide range of visual perceptions similar to how a human brain processes images. So a Bing search would turn up images of the peaks, whereas a Google search will show people climbing the peaks, graphs, maps and so on - data that is irrelevant to most ordinary searchers.
Google search results;
Bing search results
4. Duplicate detection
A common problem on the internet is the duplication of publically available images. Some images are exact duplicates while others are near duplicates (editing, cropping etc). Identifying near duplicates is a challenge due to the sheer size of the index and the millions of new images being discovered every day. Bing is continuously improving the detection process to be faster and more accurately recognize duplicates or near duplicates so you have a broader selection of images to choose from.
5. Image quality and Aesthetics
People want to see multiple images at a glance rather than dig through web pages to find the right image. This makes it easier to compare and contrast the different photos at one time. The Bing Image Search interface does a much better job at it than Google, arranging images in such a way that would make things appealing.
On Bing, when you click on an image thumbnail, a larger image appears on your screen. This allows you to fully experience the picture and quickly browse to the next. When viewing such images on your PC or tablet, it’s important that these images are of high quality with attractive elements like good contrast, lighting and composition. Relevance being equal, Bing prefers high quality images to low quality images to ensure that people have the optimal viewing experience.
Here is a video discussion between Meenaz Merchant, Senior Program Manager at Bing R&D, and Stefan Weitz, discussing image quality at Bing.
These were only some of the areas Bing is working on to improve search results quality. With the recent updates to the search engine, Bing might have enough ammunition to start taking on Google in the near future.
COMMENTS