We are asked by a couple of people if uploaded images are added to search index automatically. No. Images uploaded to GazoPa are not added to the search index, nor are they made accessible by other users automatically, unless users expressly choose to publish their photos and drawings. We added this clause in our FAQ.
Users can publish their drawings when they choose to do it. These drawings can be accessed by other users so that users can share nice search results with others.
We also received questions about rights of uploaded images from designers during our private beta. Some designers stated that our terms of service did not warrant their rights who upload their designed logo to check whether there is similar one or not. We reviewed our terms of service and clearly stated the rights of users here.
"3. User Content. User retains all copyrights and any other rights User already holds in Content which User submits, posts or displays on or through, GazoPa."
If there is any question about our service, please feel free to contact us contact (at) gazopa.com.
Friday, December 25, 2009
Wednesday, December 23, 2009
A Tip for better search results
Our current service may not always satisfy all users at the first query. Human eyes are very sophisticated systems and it's a tough job for computer vision to catch up with them. Here are tips when you encounter search results you don't expect.
1. What you can do
1) Search Option
Try search options ; shape, layout and color.
2) Face Search
At current user interface, face search are not active at the first query. If you want to find same or similar faces, set 'face' option.
3) Combined Search
Enter any keywords so that combined search, image plus keyword search, works.
2. What we can do
1) Increase database
We think the more image data we have, the better results we can return. Our search is based on similarity, so results are affected by the size of the database. I experience the results from 10 million images are much better than that from one million images. We're continuously crawling the web and the searchable data is increasing. Try our service after some interval.
2) Limit types of query
Since our database consists of various images from the web and our algorithm purely rely on color and shape, different types of images are displayed as similar results. If type of database and queries are same, more relevant results can be returned. We're preparing new service that has specific database and I think search results would be more close to what you are expecting.
3) Improve image recognition
It's ideal to develop algorithm that can detect everything in images. I don't know how many years, decade and centuries are required to make it come true, but technology is moving forward.
1. What you can do
1) Search Option
Try search options ; shape, layout and color.
2) Face Search
At current user interface, face search are not active at the first query. If you want to find same or similar faces, set 'face' option.
3) Combined Search
Enter any keywords so that combined search, image plus keyword search, works.
2. What we can do
1) Increase database
We think the more image data we have, the better results we can return. Our search is based on similarity, so results are affected by the size of the database. I experience the results from 10 million images are much better than that from one million images. We're continuously crawling the web and the searchable data is increasing. Try our service after some interval.
2) Limit types of query
Since our database consists of various images from the web and our algorithm purely rely on color and shape, different types of images are displayed as similar results. If type of database and queries are same, more relevant results can be returned. We're preparing new service that has specific database and I think search results would be more close to what you are expecting.
3) Improve image recognition
It's ideal to develop algorithm that can detect everything in images. I don't know how many years, decade and centuries are required to make it come true, but technology is moving forward.
Saturday, December 19, 2009
How many images on the web?
How many images are there on the web? No one knows exact figure. I have some data from photo sharing service as follows. Not all images on photo sharing services can be searchable, because some images are not open to public. Considering other photo sharing service such as Picasa and TwitPic and other sites that have images related news, shopping and travel etc, it may be said that four or five billion images are newly added to the web at least.
facebook 15 billion 220 million new photo per week May, 2009
flickr 4 billion 100 million new photo per month Oct, 2009
photobucket 7.5 billion June, 2009
Some images are piqued other people's curiosity such as images of Michael Jackson and Hudson river plane crash etc. Some images are too personal to be interested by general people. Photos of parties grab its participants' attention only, unless celebrities attend them. Obviously, the number of searchable images are important, but navigating users to their interested images are crucial as well. Some users are willing to see images related to shopping. Other users are eager to find images about latest news. Each user has different interest and we need to satisfy these variety of interests.
Current GazoPa.com is for general purpose use and is trying to satisfy as many types of people as possible. That's why we have filter options like news tab, video tab and flickr tab. It aims to be one stop solution to users. But we also think there should be specific type of sites that suit for specific demand. Besides improving functionalities of Gazopa.com, we're building special sites for specific needs. It'll be released at the beginning of next year. Stay tuned!
facebook 15 billion 220 million new photo per week May, 2009
flickr 4 billion 100 million new photo per month Oct, 2009
photobucket 7.5 billion June, 2009
Some images are piqued other people's curiosity such as images of Michael Jackson and Hudson river plane crash etc. Some images are too personal to be interested by general people. Photos of parties grab its participants' attention only, unless celebrities attend them. Obviously, the number of searchable images are important, but navigating users to their interested images are crucial as well. Some users are willing to see images related to shopping. Other users are eager to find images about latest news. Each user has different interest and we need to satisfy these variety of interests.
Current GazoPa.com is for general purpose use and is trying to satisfy as many types of people as possible. That's why we have filter options like news tab, video tab and flickr tab. It aims to be one stop solution to users. But we also think there should be specific type of sites that suit for specific demand. Besides improving functionalities of Gazopa.com, we're building special sites for specific needs. It'll be released at the beginning of next year. Stay tuned!
Why is it called GazoPa?
When people heard our name 'GazoPa', some responded that it was weird. Maybe. It may sound weird for people other than Japanese. We are also asked often meaning of GazoPa during conferences, so I'd like to tell you why it's called GazoPa. GazoPa comes from Japanese as you may know and Gazo means pictures and Pa is a mimetic word that describes speed of action. So, GazoPa means pictures are displayed quickly. Speed of search is one of major characteristics of our service and our name shows this feature, although only Japanese can understand background of our name. Our intention to help users to find pictures in fast speed is implied in this name.
When people heard name of new service especially in the field of Web2.0, it always sounds weird, because major name are already registered or major domain names are taken by other people, so new service needs to avoid existed ones. Besides this, shorter names such as five or six characters are preferred in Web2.0, considering the number of keys users need to type. Simple names are already taken, so new names are made from a couple of words.
When people hear the current major Web2.0 services at the first time several years ago, it might sound weird as well. But when services are getting popular, no one say these names are weird, because these names are commonly used and people get accustomed to them. So, only history will prove if name is really weird or not.
When people heard name of new service especially in the field of Web2.0, it always sounds weird, because major name are already registered or major domain names are taken by other people, so new service needs to avoid existed ones. Besides this, shorter names such as five or six characters are preferred in Web2.0, considering the number of keys users need to type. Simple names are already taken, so new names are made from a couple of words.
When people hear the current major Web2.0 services at the first time several years ago, it might sound weird as well. But when services are getting popular, no one say these names are weird, because these names are commonly used and people get accustomed to them. So, only history will prove if name is really weird or not.
Subscribe to:
Posts (Atom)
