From 1f7c71b16421cec4b7465659e93f60fffe0c6144 Mon Sep 17 00:00:00 2001 From: igraf <igraf@cl.uni-heidelberg.de> Date: Fri, 23 Feb 2024 19:41:25 +0100 Subject: [PATCH] Update paths --- project/project_proposal.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/project/project_proposal.md b/project/project_proposal.md index c7c3b28..a6a5be4 100644 --- a/project/project_proposal.md +++ b/project/project_proposal.md @@ -21,7 +21,7 @@ - some fruits are peeled, cut in half or in slices - :sparkles: the dataset is much cleaner than other fruit datasets we found on Kaggle, which often contain images of cooked food or fruit juices (e.g. [here](https://www.kaggle.com/datasets/yudhaislamisulistya/plants-type-datasets)) - + - we will narrow the dataset down to **30 types of fruits** - **29430** images @@ -43,7 +43,7 @@ - 260 x 380 pixels in example image - => 1D vector with length 260 x 380 x 3 = 296,400 - + | | Pixel 1 | Pixel 2 | Pixel 3 | ... | Pixel 381 (=second row) | ... | Pixel height x width = 98,800 | | --- | --- | --- | --- | --- | --- | --- | --- | @@ -67,7 +67,7 @@ - first ideas are: - reduce the size of the images - **edge detection** (because next to the colour, the shape of the fruit object is important) - -  + -  - concatenating edge detection with RGB values ## Which algorithms can solve our task? -- GitLab