When you are in a garden or a galary, you may be attracted by the gorgeous flawers. Then a question comes to your mind:"what's the flower's name?" It's time to ask this APP.
You can take a picture to the flower or a painting in th galary. Then upload it on the APP.
You will find the information about the flower, including its name, appearance, characteristics...
When I walking in the campus or on my way, I am always surprised by flowers or trees on the sides of roads. Then I want to know about the planet. And when I go to flower stores, I could not remember names of flowers, especially some of flowers have more than one name. Besides, flowers have their own meaning in people's communication. This feature make relationships among people romantic. However, people cannot figure out every kind of flowers, only professional staff know. Therefore, I am incentive to create an APP which can provide information of flowers by given pictures, no mater the photo of a painting or of a real flower.
You can use neural networks to recognize the content of images. ml5.imageClassifier() is a method to create an object that classifies an image using a pre-trained model.
It should be noted that the pre-trained model provided by the example below was trained on a database of approximately 15 million images (ImageNet). The ml5 library accesses this model from the cloud. What the algorithm labels an image is entirely dependent on that training data -- what is included, excluded, and how those images are labeled (or mislabeled).
Train your own image classification model with Teachable Machine: If you'd like to train your own custom image classification model, try Google's Teachable Machine.
And detail operations are below.
You could get a quick start with this code:
The initialize coding:
Mobilenet code:
Other codes:
