Scilab IPCV

Image Processing and Computer Vision Module for Scilab 6.0!

Deep Learning Inference with Scilab IPCV – Pre-Trained Lenet5 with MNIST

This is the first post about DNN with Scilab IPCV 2.0, first of all, I would like to highlight that this module is not meant to “replace” or “compete” others great OSS for deep learning, such as Pyhton-Tensor-Keras software chain, but it is more like a “complement” to those tools with the power of Scilab and OpenCV 3.4.

In this tutorial, we are going to load a pre-trained LeNet-5 model with MNIST dataset, and quickly test the model with our own handwriting. This will not take long, less than 10 lines of codes, you could load and use the pre-trained model on the fly.

(more…)

Continue Reading

What’s New in IPCV 2.0

We continue to work on IPCV module and we are pleased to announce the release of Scilab IPCV 2.0 with bugs fixed and some great new features!

Support on Deep Learning Network!

One of the exiting features in IPCV 2.0 is the support for deep learning network for inference system. This feature allows the user to import DNN models build and trained with caffe and tensorflow into Scilab to build a fast prototype or even end desktop base end solution in short time! (more…)

Continue Reading

Drawing Shapes by Overwriting Pixel Value

This post is modified from our previous blog, with our own permission. 🙂

We received some queries on the image pixels, which make us think that sometimes we might just  go too far. So let’s back to the basic for this post and coming few posts. (we might be adding some application specified application from time to time, any ideas on what you wish to see, feel free to post at the comments).

Yes, one more thing we would like to say, we do apologize on missing some posts last few weeks, due to we were focusing on the preparation of IPCV 1.2, as well as putting our public training on IPCV up and running.  Thanks for your understanding.

(more…)

Continue Reading

Official Launch of Scilab IPCV 1.2!

We are pleased to announce the release of Scilab IPCV 1.2 with bugs fixed and some new features such as high level super resolution and image stitching functions.

At the same time, our IPCV just hit 10,000 downloads at atoms portal  after 1 year it has been uploaded.

Thanks for all the support from all of you, see you next year!

Happy New Year!

Installation of Scilab IPCV 1.2

The Installation for the Scilab IPCV 1.2 for Windows 32-bits and 64-bits is the same with previous IPCV version.

As for Linux, we are trying to make IPCV 1.2 available for different Linux distributions by providing instruction for prerequisites libraries in this blogs,  and it is an ongoing process.

As for today, 17-Dec-2017, we just release the IPCV for Linux 64-bit in atoms portal, and we will provide the instructions to setup in Ubuntu, and more will be coming in near future. If you have any success in making it available in other distributions, please share with others in comment.

(more…)

Continue Reading

Object Size Estimation

In one of our previous tutorial, we had shared how to find the length of an object in an image. If you miss the tutorial, please visit this link.

One of our reader was asking whether it is possible to calculate the area for a selected region, and here we will try to work on it from the basic.

(more…)

Continue Reading

Heatmap on Google Static Maps

In the previous post we discussed about how to download the Google static map and plot the marker on given lat-long on the map. This allows the map to be reused offline.

To move further, we explore how could we use the map to visualize data on it, such as the temperature or the rainfall on the static map.

(more…)

Continue Reading

Plotting on Google Static Maps

Couple of days ago we received an inquiry on how to show the google static map and put some markers on it, let’s see how to achieve this.

In order to do so, we need to perform 2 steps:

  1. Download Google Static Map
  2. Calculate the x and y location in correspond to the lat-long given

(more…)

Continue Reading

Image Super Resolution (New Feature in v1.2)

Super Resolution is used to increase the resolution of low resolution image for better visualization purpose or for recognition purpose.

In this week post, we will again share a upcoming new feature for IPCV v1.2, –> Image Super Resolution.  In general, the are numbers of algorithms for super resolution, which works on either single image of frames of images.

In this implementation, we will use the code posted quite some time ago : Usage of sparse matrix (SparseMat) 2: Super resolution (1).

(more…)

Continue Reading