Construct a cumulative frequency table and a cumulative frequency polygon from the given frequency distribution of marks.

To do this, we add the frequency of each class to the sum of the frequencies of all preceding classes.

To draw a cumulative frequency polygon, you would plot the cumulative frequency against the upper class boundary. The points to plot are:
$(10, 0)$, $(20, 18)$, $(30, 52)$, $(40, 110)$, $(50, 152)$, $(60, 176)$, $(70, 186)$, $(80, 192)$, $(90, 200)$.
As an AI, I cannot draw the graph for you.

As an AI, I cannot draw the graph to estimate the median visually.

The total number of students is $N = 200$. The median position is $\frac{N}{2} = \frac{200}{2} = 100$.
From the cumulative frequency table, the 100th student falls into the 30-40 class (since cf at 30 is 52 and cf at 40 is 110).
The median class is 30-40.
Using the formula for the median of grouped data:

Where:
$L = 30$ (lower boundary of the median class)
$N = 200$ (total frequency)
$CF = 52$ (cumulative frequency of the class before the median class)
$f = 58$ (frequency of the median class)
$w = 10$ (width of the median class, $40-30$)

Substitute the values into the formula: