I’m pretty much agnostic

# Posts tagged with 'tips'

## It is the generation and accuracy of the ground truth corpus and annotation that has a lot of my attention. Once you have ground truth, you can erode and dilate until you find a match, or use heuristics or other segmentation methods. But it’s the “what you are attempting to conform to?” which grabs my fascination, not just with computer vision but with concepts, metaphors, any kinds of matching.

It is the generation … [read full article]

## I’m not concerned with most people. I know large swaths of folks follow predictable patterns and that hucksters take full advantage. Comedians do it for laughs, politicians for votes, magicians for an audience, actors for a convincing performance. But then, you have folks that are a bit ‘different’. To predict their behaviors, you need a different set of rules in the bag of tricks. And so on to many subsets of behavioral patterns each which require diminishing rates of return as you try to pin them down. Example: Hypothetical ruleset captures 80% of folks. Leaves you with 20%. But so what? Capture that 80% and you can go home, right? But let’s say that’s not satisfying. So, you focus on the difficult catches in that 20%. Less broad rules, far more specific. How many out of that 20% can you catch? And so on down the line. But to catch the 80%? That’s not hard. Maybe it’s 60% or 40%.

I’m not concerned with … [read full article]

## Public school is far more difficult than university. In university, you have a lot of control but in public school, you have almost none and they don’t give you all the information AND they try to trick you continually.

Public school is far … [read full article]

## Now THIS is probably the book I should’ve read first, so I’ll read it now. Morphological Image Analysis: Principles and Applications, Dr. Pierre Soille. ” Mathematical morphology (MM) or simply morphology can be defined as a theory for the analysis of spatial structures. It is called morphology because it aims at analysing the shape and form of objects. It is mathematical in the sense that the analysis is based on set theory, integral geometry, and lattice algebra. MM is not only a theory, but also a powerful image analysis technique. The purpose of this book is to provide a detailed presentation of the principles and applications of morphological image analysis. The emphasis is therefore put on the technique rather than the theory underlying MM. Besides, any non-specialist faced with an image analysis problem rapidly realises that a unique image transformation usually fails to solve it. Indeed, most image analysis problems are very complex and can only possibly be solved by a combination of many elementary transformations. In this context, knowledge of the individual image processing operators is a necessary but not sufficient condition to find a solution: guidelines and expert knowledge on the way to combine the elementary transformations are also required. Hence, beyond the presentation of the morphological operators, we will describe many real applications to help the reader acquiring the expert knowledge necessary for building the chain of operators to resolve his/her own image analysis problem. “

Now THIS is probably … [read full article]

## edian is usually better than average. I’m been experimenting with median via image skeletonization and now figured out how to do sound skeletonization. It’s the “distance transform”. Minimum euclidean distance. It keep identity intact. Nothing against gaussian but it’s mush in comparison. https://www.facebook.com/kenneth.udut/videos/10100144135248828/

edian is usually better … [read full article]

## I got help from biofeedback, administered by a psychiatrist, as a kid. But for talk therapy? I tried it 3x., one session at 17, another at 19, another at 24. Problem I had is I was saying what they were about to say before they said it. I was very annoying. I’ve had psychology as a hobby since I was a teenager, absorbing it like a sponge, did a few classes too, and thought of it as a career. Always shows up on my “What career is good for you?” in the top 3. But I didn’t because I couldn’t give advice really. Biofeedback was good. It was a solution. But talk therapy, I just didn’t understand.

I got help from … [read full article]